Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral context beyond the annotations; it repeats the obvious aggregation action. It does not mention performance implications, result limits, or the fact that aggregation can be complex/long-running. Annotations already declare read-only and non-destructive, so the agent's safety understanding is covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with no redundant words. It front-loads the core action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 params, intricate pipeline schema with $vectorSearch variants), the one-sentence description is insufficient. It omits any context about the pipeline structure, response size limits, or relation to similar tools, although the schema itself covers some of this.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description does not explain any parameter, including the critical 'pipeline' parameter which lacks a schema-level description. Schema coverage is 75% (database, collection, responseBytesLimit described), but the pipeline's meaning is left implicit. No additional semantic value is added by the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool runs an aggregation on a MongoDB collection, using a specific verb and resource. It distinguishes from siblings by mentioning 'collection' (vs aggregate-db) and 'aggregation' (vs find/count).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to choose this tool over alternatives like find, count, or aggregate-db. The only alternative mention ('export') appears in the schema's responseBytesLimit description, not the tool description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already provide readOnlyHint=true and destructiveHint=false, and the description adds no additional behavioral context. It does not mention that only database-level stages are allowed, the response size cap, or any potential side effects. Despite the annotations, the description is essentially a restatement of the tool name with no value beyond the structured metadata.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It is concise, though it omits important details; however, that omission is better captured in other dimensions.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is too sparse for a tool with an aggregation pipeline. It does not mention that this is database-level aggregation (which would differentiate it from 'aggregate'), nor does it highlight constraints like the allowed stages or response limits. The schema covers some of this, but the description fails to provide the necessary context for correct tool selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the schema itself thoroughly documents each parameter, including a link for valid stages. The description adds no extra semantic meaning, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Run an aggregation') and the resource ('a MongoDB database'), which is specific enough. However, it does not explicitly distinguish itself from the sibling tool 'aggregate', so it gets a 4 rather than a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The sibling tool 'aggregate' likely handles collection-level aggregations, but this is not mentioned. The description offers no exclusions or explicit usage scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true and destructiveHint=false, and the description aligns with these by using 'describe'. However, no additional behavioral context is offered beyond the annotations, such as prerequisites or what the output contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no filler or redundant information. It is appropriately sized for a simple tool and front-loaded with the action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with a fully documented input schema and an output schema, the description is sufficient. It states the action and resource clearly; annotations cover safety. Minor gap: no mention of needing an existing collection, but this is not critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema provides full descriptions for both parameters (database name, collection name) with 100% coverage, so the description does not need to add parameter meaning. It adds no extra detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses a specific verb ('describe') and resource ('indexes for a collection'), clearly distinguishing it from sibling tools like create-index and drop-index. The purpose is unambiguous and directly states what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit when-to-use or alternative guidance is provided. The read-only nature is implied by 'describe' but not stated, and no exclusions or alternative recommendations are given. Usage is inferred from the tool's name and relationship to siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds no behavioral context beyond that. It does not disclose that schema inference samples documents (via sampleSize) or that response size is limited by responseBytesLimit, nor any other operational traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that is front-loaded with the core action and target. Every word is necessary, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has an output schema and safe annotations, but the description is minimal. It explains the basic purpose but omits context such as how the schema is inferred (sampling) and the presence of configurable limits, leaving a competent but bare-minimum description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% parameter descriptions, so the baseline is 3. The tool description itself adds no parameter-level detail beyond what the schema already documents, so the schema carries the full burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Describe') and a clear resource ('schema for a collection'), making the tool's purpose immediately obvious. It distinguishes itself from sibling tools like 'collection-indexes' or 'aggregate' by focusing on schema structure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It does not mention prerequisites, typical use cases, or when a different tool (e.g., 'collection-indexes') would be more appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral traits beyond what the annotations already provide. The annotations declare readOnlyHint=true and destructiveHint=false, and the description merely restates the tool's name ('gets the size'). No additional context about return format, units, or performance implications is given.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with no filler or redundant information. It is well-structured and front-loaded, achieving maximum conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with two well-documented parameters and safe annotations. However, the description does not clarify what 'size' means (e.g., storage bytes vs. document count) and lacks usage guidance or differentiation from comparable tools. An output schema exists (per context), which covers return values, but the ambiguity around 'size' remains.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage with clear descriptions for both parameters ('Database name' and 'Collection name'). The tool description does not add extra meaning beyond the schema, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb and resource: 'Gets the size of the collection.' It is unambiguous but does not distinguish from related sibling tools like 'db-stats' or 'count,' which could also provide size-related information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, no prerequisites, and no exclusions. It simply defines what the tool does without contextual usage information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond the readOnlyHint/destructiveHint annotations by explaining the connection state persistence through a config resource and the idempotency-like behavior (no need to reconnect unless switching). It does not describe failure modes or what happens to the existing connection during a switch, but given the presence of an output schema and annotations, the added context is valuable and sufficient.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with the core purpose, and each subsequent sentence adds meaningful usage context. There is no redundant filler; every sentence contributes to the agent's understanding of when and how to use the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one required parameter, no nested objects), the description, combined with the schema and annotations, fully covers the necessary information. It explains the tool's purpose, connection state tracking, and when to avoid calling it. The presence of an output schema means return format does not need to be described in prose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents the connectionString parameter fully with a description that includes the expected URI format. The tool description adds no new parameter-specific semantics—it only discusses when the parameter may already be configured, which is contextual but not about the parameter's meaning or syntax. With 100% schema coverage, the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a clear, specific verb and resource: 'Connect to a MongoDB instance.' This immediately distinguishes the tool from sibling data-operation tools like find, aggregate, and create-collection. It also explains the tool's role in managing server connections, which is unique among the siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit guidance on when to call the tool and when not to: it states that if a connection string is configured or connect was already called, there's no need to call it again unless switching clusters. This gives the agent clear decision-making criteria, surpassing typical usage notes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, establishing safety. The description adds that it uses db.collection.count() and that query is optional, which clarifies the operation. However, it does not disclose potential nuances such as exact vs. estimated counts, performance implications, or behavior with large collections, so it adds only minor context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the primary purpose and includes the method name. Every word adds value, with no redundancy or extraneous detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a straightforward counting tool with an output schema present, the description covers the essential functionality and optional filtering. It does not explain return values, but the output schema likely handles that. It could mention performance limitations or distinction from similar tools, but given the tool's simplicity, the description is sufficiently complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage with clear descriptions for database, collection, and query. The description mentions query as an optional filter and relates it to the syntax of db.collection.count(). This slightly reinforces the schema but does not add substantial new meaning beyond what is already present.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Gets the number of documents in a MongoDB collection' with a specific verb and resource. It also names the underlying method (db.collection.count()), which adds precision. However, it does not explicitly distinguish this tool from siblings like aggregate or find, which can also return counts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description mentions that query is an optional filter parameter, implying the tool is used to count filtered documents. It does not provide explicit guidance on when to choose this over alternatives (e.g., find or aggregate), nor does it state exclusions or prerequisites. The usage context is present but not fully developed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false and destructiveHint=false, so the description's job is to add extra behavioral nuance. It discloses that the database is created automatically if absent, which is beyond the annotations. It doesn't mention behavior like existing-collection handling, but that is not required given the annotations provide the safety profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences that are front-loaded with the core action. Every word earns its place, and the auto-create note adds valuable context without unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two parameters, an output schema, and safety annotations, the description is adequate and covers the primary behavior. It omits edge cases like what happens if the collection already exists, but given the complexity, this is a minor gap. The presence of an output schema reduces the need to describe return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers both parameters with descriptions ('Database name', 'Collection name'), achieving 100% coverage, so the baseline is 3. The description does not enrich parameter meanings beyond the auto-create effect on the database parameter; no format, constraints, or examples are added.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Creates a new collection in a database.' The verb 'creates' and resource 'collection in a database' are specific and unambiguous, distinguishing it from sibling tools like drop-collection and rename-collection. The additional note about auto-creating the database clarifies scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage (when you need to create a collection) but provides no explicit when-to-use or alternative guidance. The auto-create behavior is a useful context cue, but no exclusions or comparisons to sibling tools like insert-many (which may also auto-create collections) are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations (readOnlyHint=false, destructiveHint=false) indicate a write operation that is not destructive, and the description's 'create' is consistent with this. However, the description adds no additional behavioral context such as performance implications, permission requirements, or side effects like index building time. With annotations present, the description contributes no extra transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, 'Create an index for a collection', which is easily scannable and contains no redundant information. It is front-loaded with the action and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complex schema with multiple index types and an output schema, the brief description is supplemented by detailed structured data. However, the description alone does not convey the breadth of supported index types or usage nuances like search indexes requiring explicit user requests, though those are documented in the schema. Overall, the description is adequate but not rich.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% description coverage for all parameters, including detailed explanations for database, collection, name, and the complex definition array with its nested variants. The tool description itself mentions no parameters, but the schema already offers comprehensive semantics, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'create' with the resource 'index' and scopes it to 'a collection', clearly conveying the tool's primary action. It distinguishes from drop-index by stating the action, though it does not explicitly mention the different index types (classic, vectorSearch, search) which the schema details. Overall, the purpose is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like collection-indexes or drop-index. It simply states the action without context about prerequisites, typical use cases, or situations where a different index-related tool should be used. This is a functional statement but lacks usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds the phrase 'use state' but does not specify what statistics are included, error handling, or behavior if the database does not exist. It provides minimal additional context beyond what the annotations imply, but it is consistent and not misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately states the purpose. It is front-loaded with the key information and contains no filler or redundancy. The length is appropriate for a tool with one parameter and no complex behavior.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only stats tool with one parameter and an output schema present, the description is mostly complete. It clearly indicates the resource and action, and the output schema handles return value details. However, the vague term 'use state' leaves some ambiguity about what statistics are included, but this is a minor gap given the output schema and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for the single 'database' parameter, with the description 'Database name'. The tool description does not add any additional meaning or examples for the parameter, so the schema already carries the full semantic load. The baseline of 3 is appropriate since the description adds no extra value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as returning statistics about a specific database, using the verb 'returns' and a clear resource. It distinguishes this from the siblings list, which includes database-level management operations like drop-database and list-databases. However, it doesn't explicitly name alternatives or elaborate on what 'use state' includes, so it's clear but not fully differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as list-databases or collection-storage-size. It does not state any prerequisites, exclusions, or scenarios where this tool is preferred. The only implied usage is that it is for retrieving statistics for one database, but no explicit context or alternative comparison is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The destructiveHint annotation already flags the destructive nature, and the description adds the scope of deletion (all matching documents). However, it fails to disclose the critical edge case that omitting the filter deletes all documents in the collection, which is a significant safety concern for a bulk deletion tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is front-loaded with the core action and resource. It contains no fluff or redundant information, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the destructiveHint annotation and schema cover many aspects, the description misses a crucial safety warning about the empty-filter case, which can delete the entire collection. Given the tool's high destructiveness, the description should explicitly caution about this behavior. The description is adequate but not complete for such an operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter (filter, database, collection) adequately described. The filter parameter includes a detailed reference to MongoDB's deleteMany syntax. The tool description itself adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Removes all documents that match the filter from a MongoDB collection' clearly states the verb (removes), the resource (documents in a collection), and the scope (all that match filter). It distinguishes itself from sibling tools like drop-collection (removes the entire collection) and update-many (modifies documents).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear context for when to use the tool: when you need to delete multiple documents matching a filter from a MongoDB collection. However, it does not explicitly mention alternatives or when-not-to-use scenarios, such as using find+delete for smaller operations or drop-collection for removing the entire collection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate destructive behavior (destructiveHint=true, readOnlyHint=false). The description adds valuable context beyond annotations by noting that associated indexes are also removed and that views are included. This discloses side effects not captured by annotations, though it doesn't discuss permissions or reversibility, which is acceptable given the destructive hint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary action, and each sentence adds value. It is concise without unnecessary elaboration, making it easy to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple destructive operation with clear annotations and an output schema, the description sufficiently covers the operation and its side effects. It is complete for an agent to understand what will happen without needing additional details about return values or prerequisites.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both parameters ('database' and 'collection') adequately described as names. The description does not add further parameter semantics, but the schema handles it. Baseline of 3 applies because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action: 'Removes a collection or view from the database.' It specifies the resource (collection or view) and the effect (removal). It also mentions associated indexes, distinguishing it from sibling tools like drop-database or drop-index. The purpose is unambiguous and specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on what the tool does, implying when to use it (when you need to remove a specific collection or view). It doesn't explicitly mention alternatives or exclusions, but the action is specific enough that the use case is evident, especially with sibling tool names available.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, so the description's mention of deleting data files is consistent but adds only minimal additional context. It does not disclose other behaviors like irreversibility, permissions, or failure modes.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence with no unnecessary words. It front-loads the core action and communicates the destructive effect efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple nature of the tool, the description covers the essential function. The destructive hint is supplemented by the annotation, and an output schema exists. Missing usage guidance is the main gap, but that is handled under usage guidelines.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with the parameter description 'Database name' being straightforward. The description does not add further meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Removes' with resource 'the specified database' and clarifies scope by adding 'deleting the associated data files'. This distinguishes it from sibling tools like drop-collection, which operate at a different level.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states only what the tool does, with no guidance on when to use it versus alternatives such as drop-collection or delete-many. No exclusions, prerequisites, or context are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false. The description does not add extra behavioral details such as irreversibility or permission requirements, but it is consistent with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that directly states the tool's purpose without unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the destructive nature, the description is minimal but sufficient because annotations and output schema cover safety and return information. It could mention side effects like permanence, but the core context is present.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides complete descriptions for all 4 parameters, including enum values for 'type'. The description adds no additional parameter semantics beyond what is already in the schema, so the score is at the baseline for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action (Drop), the object (an index), and the scope (database and collection). This distinguishes it from sibling tools like drop-collection and drop-database.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear context for the operation but does not explicitly state when to use this tool versus alternatives. No references to sibling tools or exclusions are mentioned, so usage guidance is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds the useful detail that the tool reports on the 'winning plan chosen by the query optimizer,' implying it evaluates query planning rather than just returning raw results. It also mentions 'execution,' which hints that queries may actually run to collect statistics. However, annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. No additional behavioral traits (e.g., performance implications, permission needs) are disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that front-loads the action ('Returns statistics') and specifies exactly what the statistics describe. There is no fluff, repetition, or tangential information. It is appropriately compact given the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is moderately complex (4 params, nested method schema, enum verbosity), but the extensive schema descriptions cover all parameters and their meanings. The main description provides a clear high-level purpose, and an output schema exists, so return values don't need explanation. The only gap is the lack of explicit use-case hints, but that's not a completeness issue given the schema richness and annotations.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with all four parameters (database, collection, method, verbosity) having descriptions. The main description adds no parameter-specific meaning beyond the schema. For example, the schema's verbosity description explains the trade-offs between queryPlanner and executionStats, which is richer than anything in the main text. Baseline 3 is appropriate since the description doesn't need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action and resource: 'Returns statistics describing the execution of the winning plan chosen by the query optimizer for the evaluated method.' It distinguishes this tool from siblings like find/aggregate (which execute queries and return results) by focusing on query plan analysis. The verb 'Returns' makes the primary function explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor any exclusions or prerequisites. It does not state 'use this to analyze query performance' or contrast with sibling tools. The only usage hint is buried in the schema's verbosity parameter description (e.g., use executionStats for execution time), which is about verbosity selection, not tool selection. The agent is left to infer when to invoke explain.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description only states the action without detailing behavioral aspects like whether the export is returned as a file or string, or if any side effects occur. The annotations already indicate read-only and non-destructive behavior, so the description adds no new insights.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a concise single sentence with no redundant words. It front-loads the action and clearly communicates the core function without unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool's complexity—including nested exportTarget objects for find and aggregate operations and four required parameters—the description offers minimal high-level context. It does not mention the need for database/collection or how the export is performed, making it insufficient for an agent to fully understand the tool's scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description contains no parameter-specific information, but the input schema provides comprehensive descriptions for all parameters (100% coverage). The brief mention of 'specified EJSON format' does not add value beyond the schema's detailed explanation of jsonExportFormat.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: exporting query or aggregation results in EJSON format. It uses a specific verb and resource, and the mention of EJSON format distinguishes it from sibling tools like 'find' or 'aggregate' that return data without exporting.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, such as using 'find' or 'aggregate' for direct querying. No exclusions, prerequisites, or alternative tool references are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safe read-only nature is established. The description adds no behavioral context beyond that, but it is consistent and does not contradict annotations. The schema contributes default limits and response byte caps, but those are not part of the description itself.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no filler, earning its place by specifying the target (MongoDB collection). It is appropriately short, though it could be more informative without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (7 parameters, nested objects, output schema, annotations), the description is minimal but covers the core function. It does not mention default limit or return behavior, but the schema and output schema fill those gaps. The description alone is adequate but not rich.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with detailed descriptions for all seven parameters including sort syntax, filter syntax, limit default, and responseBytesLimit. The main description adds no parameter semantics, but the schema carries the full burden, meeting the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Run a find query against a MongoDB collection'), clearly indicating a read operation. However, it does not explicitly distinguish from sibling tools like aggregate or count, though the term 'find' is a MongoDB-specific operation name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description lacks explicit when-to-use guidance. However, the schema's responseBytesLimit parameter description provides a clear alternative: if the entire query result is required, use the export tool instead. This gives some usage direction but does not cover alternatives like aggregate or count.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate this is a write operation (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds a useful performance constraint about payload size limits, but does not address other behavior like partial insert failures or ordering. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is exactly two sentences. The first states the purpose directly; the second gives a specific operational tip. No wasted words, and the key information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 3-parameter insert tool with an output schema, the description covers the main action and an important operational constraint (batching for large arrays). It does not need to explain return values because an output schema exists. The only minor gap is lack of guidance on when to choose this over alternatives, but the tool is self-explanatory.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter (database, collection, documents) already described in the schema. The tool description only paraphrases 'array of documents' without adding new parameter-level information, so it stays at the baseline for high coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description says 'Insert an array of documents into a MongoDB collection,' which is a specific verb+resource statement. It clearly distinguishes this from sibling tools like delete-many, update-many, and aggregate by naming the exact operation and target.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear usage guideline for large payloads: 'If the list of documents is above com.mongodb/maxRequestPayloadBytes, consider inserting them in batches.' This gives the agent actionable context, though it does not explicitly mention alternatives or when-not-to-use scenarios.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, which fully covers the safety profile. The description adds minimal behavioral context beyond the scope of 'all collections', but no additional info is necessary.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of seven words, front-loaded with the verb and resource. Every word contributes value and there is no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one required parameter and an output schema. The description sufficiently conveys the scope of the operation, and the output schema covers return values, making it adequately complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage for the single parameter with a description of 'Database name'. The tool description reinforces the role of the database parameter but adds no extra meaning, so the baseline applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action (List) and resource (collections) with a qualifier (for a given database). This distinguishes it from sibling tools like list-databases and collection-schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The context is clear: use this when you need to enumerate all collections in a specified database. No explicit alternatives or exclusions are mentioned, but for this simple operation the implied usage is adequate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds minimal behavioral context beyond the annotations, such as no mention of pagination or return format. This meets the baseline but does not provide extra value beyond what the annotations already convey.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that is front-loaded with the verb 'List' and directly states the action and resource. Every word is meaningful, with no redundancy or filler. This is an example of efficient structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with no parameters, and the annotations provide the safety profile. An output schema exists to document return values, so the description does not need to explain them. The description adequately covers the tool's purpose for an agent, making the definition complete for this straightforward operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and an empty input schema, so there is no parameter information to convey. The description correctly implies that no arguments are required. A baseline score of 4 is appropriate for empty parameter lists, as the description adds no unnecessary parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List') and resource ('databases'), clearly stating the tool's function as listing all databases for a MongoDB connection. This distinguishes it from sibling tools such as 'list-collections' by specifying the scope of databases rather than collections.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates the context of use: listing databases for a MongoDB connection. However, it does not explicitly mention alternatives or exclusions, such as noting that 'list-collections' should be used for collections instead. This is a minor gap, so it earns a 4 rather than a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is established. The description adds context about the knowledge base and its role in finding filter parameters, but it does not provide additional behavioral details such as pagination, output format, or side effects. This meets the expected bar for a simple listing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is only two sentences, front-loaded with the action verb and resource. The second sentence adds practical usage guidance without any redundant fluff. Every word contributes to the tool's understanding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only listing tool with no parameters and no output schema, the description is complete: it states what is listed, where (MongoDB Assistant knowledge base), and why it is useful (exploration and finding search filter parameters). It could mention the return format, but that is not critical for a list tool with such clear purpose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the schema description coverage is vacuously 100%. Per the baseline rule for 0-parameter tools, the score is 4. The description does not need to explain parameters, and it correctly mentions that filter parameters for search-knowledge can be discovered from this tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: listing available data sources in the MongoDB Assistant knowledge base. It is specific with a clear verb and resource, and distinguishes itself from sibling tools like list-collections and list-databases by focusing on the knowledge base and referencing search-knowledge.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly tells users when to use this tool: to explore data sources or to find filter parameters for search-knowledge. It provides clear context for its use, though it does not explicitly mention alternatives or when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds context that logs are returned in reverse chronological order (most recent first), but it does not disclose details like the default limit, maximum entries, or behavior when no logs exist. Since annotations cover the main behavioral risk, a score of 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that conveys the core purpose without extraneous words. It is front-loaded with the verb and resource, making it quickly scannable by an agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of a fully described input schema (100% coverage) and an output schema, the description sufficiently covers the tool's purpose and scope. For a simple read-only log retrieval tool, this is complete; the schema handles parameter constraints and return format details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents the 'type' and 'limit' parameters. The description adds no additional parameter-level semantics beyond what the schema provides, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns the most recent logged mongod events, using a specific verb (returns), resource (mongod logs), and scope qualifier (most recent). This distinguishes it from sibling tools like find or aggregate, which operate on collections rather than server logs.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention exclusions or prerequisites. For example, it does not clarify whether this is for server diagnostics vs. database operations, or when a user might prefer a different read tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral context beyond the basic rename operation. Annotations indicate non-read-only and non-destructive, but the description does not explain side effects, such as behavior when the target exists (covered only in schema) or any impact on dependent references.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single succinct sentence that front-loads the core action. It contains no unnecessary words and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple operation, the description is minimally adequate. The schema covers parameters and an output schema exists. However, it lacks usage context and critical behavioral details (e.g., what happens if the target collection exists), which are only implicitly addressed in the parameter description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description itself adds no parameter-specific detail, but the schema fully documents each parameter, including dropTarget's behavior, so no additional semantics are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the operation: 'Renames a collection in a MongoDB database.' It uses a specific verb and resource, distinguishing it from sibling tools like create-collection or drop-collection.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention exclusions or prerequisites, leaving the agent without context for optimal tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds context about the content scope (official documentation, curated guidance) but does not disclose return behavior, pagination, or any other caveats. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary action, and contains no unnecessary detail. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple search tool with no output schema and fully described parameters, the description sufficiently covers purpose, content scope, and filtering. The schema covers parameter details, and annotations cover safety, so no significant gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with all three parameters (query, limit, dataSources) fully described. The main description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: searching the MongoDB Assistant knowledge base, with explicit scope (official docs, curated guidance) and filtering capabilities. It distinguishes itself from sibling tools like list-knowledge-sources and database operations.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context on when to use this tool (searching the knowledge base) and mentions filtering by data source/version, but does not explicitly name alternatives or exclusions. The schema's dataSources description mentions list-knowledge-sources, but this is not in the main description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds the batching consideration, which is a useful operational detail. However, it does not disclose other behavioral traits such as the potentially large scope of updates, atomicity, or irreversibility, which are relevant for a mutation tool. The annotations already indicate it is not read-only, so the description adds moderate context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences: the first clearly states the core action, and the second adds a useful operational tip. There is no redundancy or wasted wording.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description, combined with the thoroughly documented input schema and presence of an output schema, provides sufficient context for basic use. It covers the main behavior and includes a batching tip. Minor gaps exist (e.g., not mentioning atomicity or side effects), but these are not critical given the schema completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers all parameters with 100% description coverage, so the schema carries the burden. The description does not add any parameter-specific semantics beyond what is in the schema, earning the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool updates all documents matching a filter in a collection, using the specific verb 'Updates' and identifying the resource. This distinguishes it from sibling tools like delete-many, find, and insert-many.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a practical guideline about batching updates when the payload exceeds a size limit, implying when to use this tool. However, it does not explicitly mention alternatives or when to prefer this over similar tools, leaving usage context partially implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.