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

No annotations are provided, so the description carries the behavioral burden. It states that the tool 'explain[s]' content, but it does not disclose output format, whether it returns static text, or any side effects. For a zero-parameter explanation tool, this is minimally adequate but not rich.

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 immediately states the tool's purpose. Every word contributes value, and there is no redundant or filler content.

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 orientation tool with no inputs and no output schema, the description is sufficiently complete for an agent to select and invoke it. It could arguably name example source-combination patterns, but that is not necessary for basic correct use.

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 coverage is 100%, so there are no parameter semantics to clarify. The description adds no parameter info, but none is needed; the baseline for a no-parameter tool is met.

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's role as an orientation/explanation tool: it explains what the MCP is useful for and how to combine sources. This is distinct from sibling tools like list/get/search, making its purpose 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 implies the agent should use this tool to understand the MCP's overall utility and source-combination strategy, which is clear context for when to invoke it. It does not explicitly state exclusions or alternatives, but the purpose itself is the 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?

No annotations are provided, so the description carries the burden. It discloses that the tool fetches an excerpt (read operation) and that it's from a curated source, but it doesn't mention any limitations, such as whether the excerpt is truncated, how it handles missing sources, or any rate limits. The description is adequate but not rich in behavioral detail.

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 purpose and includes a key usage hint. No wasted words; it 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 tool's simplicity (2 params, no output schema, no annotations), the description is fairly complete. It explains the source_key format and the excerpt nature. It could mention what happens if the source is not found or if max_chars is exceeded, but for a simple fetch tool, this is adequate.

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 both parameters are documented in the schema. The description adds a bit of context by explaining that source_key can be a number, title keyword, or URL fragment, which goes beyond the schema's generic description. However, it doesn't add much for max_chars beyond what the schema already provides (default, min, max). Baseline 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 fetches a short text excerpt from a curated source URL, with a specific verb ('fetch') and resource ('source excerpt'). It distinguishes from siblings by focusing on excerpts from curated sources, though it doesn't explicitly contrast with other tools like get_sources or get_dataset.

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 usage context: it tells the agent to use source_key as a number, title keyword, or URL fragment from get_sources. This implies when to use it (after getting sources) and how to reference sources, but it doesn't explicitly state when not to use it or mention alternatives.

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; description says 'inspect' suggesting read-only, but does not explicitly confirm no side effects, error cases, 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?

Single, concise sentence that communicates the essential purpose 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?

Adequate for a simple get operation; does not describe return format, but this is not required given the simplicity and lack of 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?

Schema already describes 'dataset' as slug or id; description does not add extra meaning beyond what the schema provides.

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 it inspects a single dataset via slug or id, distinguishing it from siblings like list or search.

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?

Implies use when you have a specific dataset identifier, but does not explicitly contrast with search/list or other alternatives.

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 full burden. It only says 'List' without disclosing whether this is a read-only operation, if it returns a fixed list or accepts filters, or any other behavior. No indication of network calls, caching, or response size.

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?

One concise sentence, no fluff, and it front-loads the key action. However, it is so minimal that it might be seen as under-specified rather than appropriately concise, but for a parameterless listing tool it is acceptable.

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 output schema, no annotations, and easy sibling confusion, the description is insufficient. It doesn't mention what kind of sources are returned (e.g., URLs, names, metadata), nor how it differs from other listing tools. Could benefit from a sample output or a note on 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 tool has zero parameters and the schema coverage is 100% (empty object). The description adds a minimal value by clarifying that sources are 'curated official and high-value', which is not in the schema. With no params, a baseline of 4 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 states a specific action ('List curated official and high-value sources') with a resource ('Outre-mer'), but it lacks differentiation from sibling tools like outremer_search_data_gouv or outremer_list_reference_items. It is clear but does not distinguish what makes these sources unique versus other listing tools.

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 on when to use this tool versus alternatives. Sibling tools like outremer_search_data_gouv and outremer_list_reference_items could overlap, but no exclusions or context are provided. The description implies a static listing but gives no criteria for when to choose 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?

With no annotations provided, the description carries the full burden. It discloses that the tool returns 'public-data search hints' rather than actual data, which is useful behavioral context, but it omits details such as error handling, network dependencies, or whether the operation is read-only. There is no contradiction with annotations since none exist.

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 front-loads the verb and resource, with no wasted words. Every element 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?

For a simple one-parameter tool, the description covers the core purpose and output type, but the term 'public-data search hints' is vague and no output schema exists to clarify the return structure. It also lacks guidance on relationship to sibling tools, making the description sufficient but not fully 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 already describes the single parameter 'territory' with examples, achieving 100% coverage. The tool description adds the phrase 'by name or code,' which slightly reinforces the schema but does not provide substantial additional meaning. Following the baseline for high schema coverage, a 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 uses the specific verb 'Resolve' with a clear resource ('one French overseas territory') and explicitly states the input type ('by name or code') and output ('public-data search hints'). This distinguishes it from sibling tools like outremer_list_territories (listing all) and outremer_search_territory_datasets (searching datasets).

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 does not explicitly state when to use this tool over alternatives. While the purpose implies it is a preliminary resolution step for searching public data, it does not mention any exclusions or alternative tools, leaving the agent to infer usage 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, the description bears the burden of behavioral disclosure. It adds value by naming the upstream API (geo.api.gouv.fr) and explicitly listing the valid department codes (971, 972, 973, 974, 976). However, it doesn't mention side effects, authentication, or error behavior. Given the simple read-only nature of listing communes, this is adequate but not excessive, scoring a 3.

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 sentences, front-loaded with the primary purpose and immediate supporting details. Every word earns its place, with no fluff or 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?

For a straightforward list operation with one parameter and no output schema, the description covers the essentials: the action, the target (communes), the scope (overseas department), and valid inputs. While it doesn't detail return format or error handling, the simplicity of the tool makes this acceptable, though a mention of output structure could push it to 5.

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 documents the single parameter 'department_code' with a description ('Overseas department code.') and an enum of valid values. The tool description repeats the enum values, adding no new semantic depth. Since schema coverage is 100%, the description adds no extra parameter insight, keeping it at the baseline 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 'List communes for an overseas department' with a specific verb and resource. It also identifies the external API (geo.api.gouv.fr) and lists supported department codes. While it doesn't explicitly distinguish from sibling tools, the resource (communes) is distinct and the supported codes add specificity.

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 when to use the tool—when listing communes for an overseas department—but doesn't explicitly discuss alternatives or exclusions. The context of supporting specific department codes is clear, but there's no 'use this instead of X' guidance. This is merely implied usage, fitting a score of 3.

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 present, and the description does not convey behavioral details such as read-only nature, potential side effects, or what happens when no reference items are available. The 'when available' clause is vague.

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 unnecessary words or redundancy. It effectively communicates the core purpose without extra fluff.

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 minimal and does not explain what reference items are, the expected output format, or how they might be used. Since there is no output schema, the description should provide more context about the return value, but it lacks detail.

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 takes no parameters, so the baseline of 4 applies. The description correctly indicates an empty schema and no additional parameter explanations 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 action: listing built-in reference items. It is a specific verb and resource, distinguishing it from sibling tools like list_territories or get_sources.

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 phrase 'when available' hints at conditional availability but does not explain the intended use case or 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, the description must clarify behavior. It accurately conveys that the tool returns a list (implying read-only) and even describes the payload (INSEE codes, portal hints). However, it does not explicitly discuss potential side effects, that it is safe to call repeatedly, or any data freshness considerations, leaving some ambiguity for a tool with no 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, well-structured sentence that leads with the key verb and subject, then adds specific detail without any filler. Every word earns its place, making it exceptionally scannable for 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?

For a parameter-less list operation, the description covers the essential elements: what is being listed, what field data to expect (INSEE codes), and an example of rich content ('useful portal hints'). It could go slightly further by noting whether the output is flat or includes nested territories, but given the simplicity of the tool, this is a harmless 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?

The tool accepts zero parameters, so the input schema is trivially 100% covered. The description needs to explain nothing about parameter formats or defaults. This hits the baseline of 4 for parameter-less tools, and the description even adds value by noting what the returned list contains, which is complementary.

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 is precise and actionable: 'List French overseas territories' clearly identifies the verb and resource, and the inclusion of 'INSEE department/collectivity codes and useful portal hints' makes the tool's output distinctive, setting it apart from similar tools like outremer_list_communes.

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 guidance is provided on when to use this tool versus alternatives such as outremer_get_territory or outremer_list_communes. While the verb 'List' implies a general overview, the description does not mention when one might need detailed territory information or how to drill down, leaving usage context to be inferred.

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 of behavioral disclosure. The phrase 'official public API' mildly implies a free, authentication-free endpoint, which is useful context. However, there's no mention of pagination behavior, rate limits, error handling, or what the default query behavior is when no parameters are supplied.

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?

A single, front-loaded sentence with zero wasted words. The key action (search) and resource (datasets on data.gouv.fr) are conveyed immediately with no fluff.

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 relatively simple search tool with 2 optional parameters, minimal documentation might be acceptable. However, with no annotations, no output schema, and an ambiguously-scoped sibling (outremer_search_territory_datasets), the description leaves important gaps—what does an empty query return, how does pagination work, what does the response look like? These are unaddressed.

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% (both query and page_size are documented with descriptions). The description itself adds no parameter-level detail, but per the rubric baseline, when schema coverage exceeds 80%, a score of 3 is appropriate since the schema already handles parameter documentation.

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?

Clear verb+resource: 'Search public datasets on data.gouv.fr' is specific and understandable. However, it fails to differentiate from the similarly-named sibling 'outremer_search_territory_datasets', which could create confusion about which search tool to invoke.

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 on when to use this tool versus alternatives. Given multiple search-related siblings (outremer_search_territory_datasets, outremer_get_dataset), explicit disambiguation would be highly valuable but is entirely absent. There's no when-to-use or when-not-to-use 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 indicates a read-only search operation, but it does not explicitly state that it is non-mutating or mention any side effects, permissions, or rate limits. The lack of annotations leaves some ambiguity about behavior, though the nature of a search suggests safety.

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, well-structured sentence that directly conveys the tool's purpose without unnecessary words. It is appropriately sized and easy to understand.

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 provides enough context for the tool's intended use, including the data source and scope. It does not describe the return format or output, but that is acceptable given the absence of an output schema and the simplicity of the search task.

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 descriptions fully cover the parameters (territory, topic, page_size) with clear examples and constraints. The description adds no extra meaning or usage details beyond the schema, so it meets 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 states the tool's function: searching data.gouv.fr for datasets related to a specific French overseas territory. It is concise and distinguishes the action from sibling tools like listing territories or getting sources.

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 the tool should be used when a dataset search for a particular territory is needed, but it does not explicitly specify when to prefer this over alternatives. It lacks explicit guidance on 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.