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

No annotations were provided, but the description does not disclose any behavioral traits such as permissions needed, performance implications, or side effects. It only describes input/output without addressing costs or limitations.

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 concise, front-loaded with the main purpose, and includes inline examples. Every sentence adds value without 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 description explains the return format and optional filtering, and an output schema exists. It covers the core functionality but omits error scenarios or rate limits, which are minor given the tool's simplicity.

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 adds significant meaning to the 'where' parameter with examples and default behavior, but the required parameters (account, database, container) lack additional context beyond their names. With 0% schema description coverage, the description partially compensates but not fully.

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 'Count items in a Cosmos DB container' using a specific verb and resource. It explicitly contrasts with siblings like cosmosdb_query_items (which returns items) and provides distinct functionality.

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 explains when to use the tool (counting with optional filter) and provides examples for the where clause. It implies alternative tools but does not explicitly state when not to use this 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?

Given no annotations, the description carries the full burden of behavioral disclosure. It explicitly warns that 'THIS IS DESTRUCTIVE — the item cannot be recovered after deletion,' which is a key behavioral trait. It does not, however, mention potential side effects (e.g., cascading deletes) or authentication/rate limit considerations, but the core destructive behavior is well-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 extremely concise: two key sentences stating purpose and requirement, plus a critical warning. Every sentence adds value, and the structure front-loads the action and immediate usage constraints.

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 5 required parameters and is destructive. While the output schema exists (so return values are not needed in description), the description omits guidance on how to obtain required identifiers (e.g., item_id and partition_key) or error behavior. It adequately covers the irreversibility but lacks completeness for a complex 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 0%, so the description should add meaning for all parameters. It only mentions 'item_id' and 'partition_key,' leaving 'account,' 'database,' and 'container' completely unexplained. The schema itself provides titles but no descriptions, so the agent gets no additional context beyond the parameter names.

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 'Delete an item from a Cosmos DB container.' It uses a specific verb ('Delete') and resource ('item'), making the action unambiguous. Among siblings like 'read_item' and 'upsert_item', this tool's purpose is distinct and immediately understandable.

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 emphasizes that both 'item_id' and 'partition_key' are required, which is critical for correct usage. However, it does not explicitly state when to use this tool over alternatives (e.g., when to delete vs. update) or provide 'when not to use' guidance. The destructive nature is clearly flagged, but contextual usage hints from sibling names are indirect.

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?

With no annotations provided, the description discloses that this is a read-only metadata retrieval operation, listing system properties (_self, _etag, _ts). It does not mention permissions, cost implications, or failure scenarios, but the core behavioral trait (non-destructive read) is clear.

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 concise, with two short paragraphs. The first sentence states the primary purpose, followed by a bullet-like list of returned metadata. The second paragraph adds a useful usage hint. Every sentence is valuable with 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?

Given the simple parameter set (3 required strings) and the presence of an output schema, the description adequately covers the tool's functionality. It lists the returned fields, which complements the output schema. It could mention required permissions or that the tool returns system properties, but overall it is fairly 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?

Schema coverage is 0%, but the description adds meaning for the 'account' parameter by noting it can be a short name or full endpoint URL. However, 'database' and 'container' parameters receive no additional explanation beyond their names, leaving ambiguity in the context of Cosmos DB.

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 retrieves metadata for a Cosmos DB container, listing specific fields like partition key path and indexing policy. It is easily distinguishable from siblings such as cosmosdb_list_containers (which lists containers) and cosmosdb_read_item (which reads an item), as this tool focuses on container-level metadata.

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 usage hint about the account parameter (short name or full URL) but gives no explicit guidance on when to use this tool versus alternatives like cosmosdb_list_containers or cosmosdb_query_items. It does not mention prerequisites or common use cases.

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?

With no annotations, the description covers key behaviors: it lists all accounts, auto-resolves subscription, and returns error if no subscription available. It does not describe return format, but output schema exists to cover that.

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?

Two concise sentences with front-loaded purpose. No wasted words, every sentence adds value.

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 no parameters and an output schema, the description is complete: it explains subscription resolution and error cases. No additional information is necessary.

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; baseline is 4. No additional semantic value needed beyond the schema, which is trivially covered.

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 'List all Azure Cosmos DB accounts in the current subscription,' with a specific verb and resource. Among siblings, it's the only tool for listing accounts, so it's well-distinguished.

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 explains subscription resolution (environment variable then az login) and error handling, providing clear context for usage. It does not explicitly mention when not to use, but for a simple list tool, this 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?

With no annotations, the description should disclose behavioral traits. It mentions the output format and account flexibility but does not discuss side effects, permissions, or if it is read-only. Adequate but lacks depth.

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 concise with two sentences, no redundant information, and is well-structured. Every sentence adds value.

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 covers the tool's purpose, input format, and output format. Since an output schema exists, return values are documented. It is complete for a simple list 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 coverage is 0%, so description must compensate. It adds meaning for 'account' (short name or full URL) but provides no additional clarity for 'database'. Adds some value but not enough for all parameters.

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 verb 'list' and the resource 'containers in a Cosmos DB database', and specifies that the output is a sorted JSON array. It differentiates from sibling tools like cosmosdb_list_databases.

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 explains what the tool does but does not provide explicit guidance on when to use it versus alternatives like cosmosdb_get_container_info or cosmosdb_list_databases. Usage context is implied but not stated.

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?

Discloses automatic URL normalization and return format (sorted JSON array). No annotations exist, so description carries full burden; lacks details on authentication or rate limits.

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?

Three focused sentences: purpose, return format, and parameter flexibility. No extraneous information.

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?

Covers key aspects: what the tool does, input format, and return type. With one parameter and implied output schema, it 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?

Schema has a single parameter with no description; the description adds significant meaning by explaining account can be short name or full URL and will be normalized.

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?

Clearly states 'List all databases' with the specific resource (Cosmos DB account) and return format, distinguishing it from sibling tools like cosmosdb_list_accounts or cosmosdb_list_containers.

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?

Provides helpful context on how to specify the account (short name or URL) but does not explicitly state when to use this tool vs 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?

No annotations are provided, so the description carries the full burden. It discloses that max_items is capped at 1000, cross-partition queries are enabled automatically, and the SQL syntax expected. These are key behavioral traits for a query tool. However, it does not mention error handling or response format, though an output schema likely covers the latter.

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 concise: three sentences plus a code block, with the purpose stated in the first sentence. It is front-loaded and every sentence adds value—purpose, examples, constraints, and alternative tool recommendation—with no unnecessary information.

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 (5 parameters, SQL queries) and the presence of an output schema, the description covers the key aspects: query syntax, result limit, cross-partition support, and alternative tool. It does not cover error scenarios or performance characteristics, but these are reasonable omissions for a query tool with an output schema.

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?

With 0% schema description coverage, the description adds meaning for two of five parameters: it explains query syntax and max_items cap (overriding default). Account, database, and container are not described, but their names are self-explanatory. The description does not fully compensate for the lack of schema descriptions, but adds enough value to meet baseline.

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 a SQL query against a Cosmos DB container and returns results, with examples of SQL syntax. It distinguishes itself from the sibling tool 'cosmosdb_query_items_to_file' by mentioning when to use that alternative, fulfilling the purpose clarity criterion fully.

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 not to use this tool ('Use cosmosdb_query_items_to_file instead if the result set may be large'), but does not cover when to use it over other read-related siblings like 'cosmosdb_read_item'. The cross-partition automatic enablement is mentioned, providing useful context.

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?

With no annotations provided, the description covers key behaviors: writes to file as JSON array, returns only item count, and caps max_items at 1000. Could be improved by mentioning file overwrite behavior.

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 very concise, with front-loaded purpose and additional details in short sentences. No redundant information.

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 an output schema, the description's mention of return value (item count) and file output is sufficient. Minor gaps remain around error handling and file overwrite behavior.

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 0%, but description only adds meaning for output_file and max_items (cap). The main parameters account, database, container, query are not elaborated beyond their basic role in a query.

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 a SQL query and saves results to a file, distinguishing it from sibling tools like cosmosdb_query_items which likely return results in context.

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?

It explicitly advises using this variant when result sets may be large to avoid filling the context window, and mentions the max_items cap of 1000.

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?

No annotations are provided, so the description carries the full burden. It mentions returning the full item document as JSON and implies no side effects, but does not disclose error handling (e.g., item not found), permission requirements, or rate limits.

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 concise sentences with clear structure: purpose, return value, and a required-parameter rationale. No wasted 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?

With 5 required parameters and an output schema, the description is mostly complete for a simple read tool, but it fails to explain account, database, and container parameters, which is a notable gap.

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 0%, so the description should compensate. It only explains item_id and partition_key, but not account, database, or container. This leaves 3 of 5 parameters undocumented in meaning.

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 'Read a single item' with the specific verb and resource, and distinguishes from siblings like query_items or upsert_item by focusing on point reads by ID and partition key.

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 explains that both item_id and partition_key are required and why partition key is needed for efficient point reads. However, it does not explicitly state when not to use this tool or mention alternatives for different 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?

No annotations provided, so description carries full burden. It discloses the 'id' requirement, upsert behavior, and return value (stored item with system fields). Missing details on partition key handling, error conditions, or permissions.

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?

Three sentences, front-loaded with the core action, no wasted words. Structure is logical: action, requirements, behavior, return value.

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 4 parameters with no schema descriptions and no annotations, the description covers the key points: required id field, upsert behavior, and output format. Does not discuss error handling or edge cases, but adequate for a simple 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 input schema has 4 parameters with 0% description coverage. The description adds meaning by clarifying the 'item' parameter must include an 'id' field and that the partition key is considered. Other parameters are standard Cosmos DB identifiers.

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 purpose with a specific verb ('Insert or replace') and resource ('an item in a Cosmos DB container'). It distinguishes from sibling tools like cosmosdb_read_item (no replacement) and cosmosdb_delete_item.

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 explains when to use the tool: for items with an 'id' field, with replacement logic based on id and partition key. It does not explicitly list when not to use it or compare to siblings, but the behavior is clear.

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