Wikimedia Enterprise docs

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful behavioral context: it accepts a `#section` suffix, and it maps specific id prefixes to different content types (markdown guide, OpenAPI endpoint, response model). This goes beyond the schema's generic 'id returned by search'.

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, dense sentence that front-loads the core purpose ('Full text for one id from `search`') and then efficiently enumerates the accepted id forms. Every clause earns its place; there is no filler or repetition of schema 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 single-parameter read tool with an output schema and readOnly/idempotent annotations, the description is nearly complete. It explains the id format variants and even notes special cases like `docs/changelog` and `docs/pricing`. The only minor gap is that it doesn't describe error behavior for invalid ids, but that is not essential given the output schema and simple parameter.

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 already documents the `id` parameter. The description adds meaningful format details (e.g., `docs/<slug>`, `op/<operationId>`, `schema/<name>`) that the schema does not provide, but since the schema already covers the basic semantics, a 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 names a specific verb ('Fetch') and resource ('one id from `search`'), then enumerates the three accepted id forms (`docs/<slug>`, `op/<operationId>`, `schema/<name>`) with concrete examples. This clearly distinguishes it from siblings like `search` and `get_endpoint`.

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 states the tool is for fetching full text for one id returned by `search`, which implies it should be used after `search` and not for listing or searching. It does not explicitly name alternatives or exclusions, but the id-source constraint and the sibling set make the usage context clear.

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 carry readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: output is 'dereferenced from the OpenAPI definition (the source of truth)', informing the agent that $ref pointers are resolved, and that results come as 'structured JSON plus a markdown rendering'. No contradiction with annotations; the read behavior is consistent with readOnlyHint.

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 with zero filler. The core purpose is front-loaded, and the second sentence delivers the identification logic. Every clause earns its place; no redundant restatement of the title or annotations.

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 an output schema present, the return structure is documented externally, so the description need not re-explain it. It covers the dereferencing behavior and the selection logic. The only minor gap is error behavior when an endpoint cannot be found, which is acceptable given the readOnly/idempotent annotations and available 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 coverage is 100%, so all three parameters (path, method, operationId) are already documented. The description adds value beyond the schema by explaining the parameter relationship: the endpoint can be identified by operationId OR by method+path, which clarifies that the parameters are alternative selectors rather than jointly required — essential given 0 required 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 states a specific verb and resource: it returns 'the exact request and response shape of one endpoint'. It clearly differentiates from siblings — list_endpoints ('one endpoint' vs. listing) and search — and specifies both the output format ('structured JSON plus a markdown rendering') and the identification keys (operationId or method+path). An agent can distinguish this from fetch/list_endpoints/search without inspecting schemas.

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 tool to retrieve the dereferenced shape of a single endpoint, and the description gives concrete identification guidance ('Identify it by operationId, or by method and path'). It does not name sibling alternatives or explicit when-not scenarios, but given siblings like list_endpoints and search, the singular-scope wording makes the intended usage unambiguous.

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, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds useful behavioral context beyond annotations: endpoints are returned 'in reference order' and each includes three specific pieces of information. This helps the agent set expectations about the response structure.

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 with no filler: the first delivers the core purpose and output shape, and the second explains the optional filter with an exhaustive tag list. Everything present 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 list-all operation with one optional parameter and an output schema, the description is complete. It covers scope, ordering, output contents, and filtering, leaving no material gap for an agent to call it correctly.

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% for the tag parameter, so the schema already provides a baseline. The description adds significant value by enumerating the exact allowed tag values and clarifying that the tag is a filter, which is more actionable than the schema alone.

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 resource ('every endpoint in the Wikimedia Enterprise OpenAPI definition') and the exact form of the output ('technical title, plain-language line, link into the reference'). The strength of 'every' distinguishes it from siblings like get_endpoint and search, which are clearly about individual or filtered retrieval.

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 explains the filtering capability and lists all valid tags, giving an agent concrete guidance for using the tool. However, it never mentions when to prefer this tool over siblings such as get_endpoint or search, leaving the alternative-selection logic implicit 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?

Annotations already cover safety (readOnly, idempotent, closed-world), so the description's added value is the query-mode behavior and the id-handoff return contract, both useful beyond structured fields. It says nothing about result ranking, whether the whole corpus is indexed, or how `limit` affects results, which keeps it from a 5.

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 tight sentences: what it searches, how to query it, what you get back. The corpus scope is front-loaded and every clause carries information an agent would otherwise have to guess.

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 an output schema present, the description only needs to say what comes back, which it does ('ids to pass to `fetch`'). Combined with the query-phrasing guidance, an agent has enough to call it correctly; the silent `limit` parameter and unspecified ranking/pagination behavior are the remaining gaps.

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 67% — `query` and `scope` are documented inline, while `limit` has no description anywhere. The description reinforces query syntax with concrete token examples, which is genuine added meaning, but it never mentions `scope` or the result-count cap, so it doesn't compensate for the coverage gap.

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?

States a specific verb ('Full-text search') and names the exact resource scope: guide sections, changelog, pricing, endpoints and response models. The closing sentence ('Returns ids to pass to `fetch`') separates it from the fetch sibling, and the resource framing distinguishes it from list_endpoints/get_endpoint without opening any 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?

Gives concrete guidance on how to phrase queries ('exact tokens work best... plain questions work too') and the follow-up step ('ids to pass to `fetch`'). It stops short of explicitly saying when to prefer get_endpoint or list_endpoints for a known endpoint name, so the routing against the other two siblings is left implicit.

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