pmndrs docs

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real content-level disclosure: the response includes what the example demonstrates, the pinned dependency versions, and every source file. It omits any note on payload size or truncation for large examples, which is the only remaining gap.

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, each earning its place: what it returns, the parameter constraint, and the routing rule. Front-loaded with the action and scope, with the disambiguation last where it belongs.

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 no output schema, the description carries the burden of explaining the return shape and does so ('what it demonstrates, the exact versions..., every source file'). For a single-parameter read tool, nothing an agent needs before calling is missing.

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% and the single parameter is fully documented in the schema. The description's instruction to take `name` verbatim from examples://index largely restates the schema's own description, adding a source-of-truth hint but no new semantics. Baseline 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?

States a specific verb ('Read one') and resource ('pmndrs example') plus the exact scope of what is returned: purpose, versions, and every source file. It also names the sibling route (search_docs then get_page_content) for a different question type, so an agent can distinguish it without opening a 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?

Explicitly gives the selection condition ('Reach for an example when the question is how a scene is put together') and the exclusion/alternative ('for what an API takes, search_docs then get_page_content'). Both when-to-use and when-not-to-use are covered, which is rare.

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 destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: exact path matching, per-library path shape variation, and that the return is current markdown. It stops short of error/failure behavior but is strong for a read tool whose safety is already annotated.

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, front-loaded with what it does, then the exact-match constraint, then the routing instruction. Every sentence carries actionable information with no padding.

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 2-parameter read tool with full schema coverage and annotations covering safety, this is complete: it states the return format (markdown), the strict input provenance, and the prerequisite alternative tool. Nothing an agent needs to invoke it correctly is missing.

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 the baseline is 3, but the description adds real meaning: take lib and path 'verbatim' from a search hit, paths are matched exactly, and their shape differs per library so they must never be guessed or adapted. This clarifies the required provenance and validation behavior beyond the schema's field descriptions.

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 and resource ('Read one documentation page in full, as current markdown') and implicitly distinguishes itself from search_docs and get_example by being the full-page reader. An agent can tell what it does and how it differs from retrieval/search 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?

Explicitly routes the agent: 'Call search_docs first when you do not have a path yet.' It also names the docs://{lib}/index resource as an alternative source of lib/path, giving clear when-to-use guidance with no inference required.

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 destructiveHint=false, so the safety profile is covered. The description adds non-annotation behavior: it returns exactly 10 best-matching pages ranked best-first, each with a lib and path. It does not mention rate limits or auth, but for a read-only search that is a minor omission.

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 critical instruction (call this first) and the staleness rationale are front-loaded in one dense sentence, followed by the return shape. No filler sentences; every clause carries actionable 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?

With no output schema, the description supplies the missing return contract (10 results, ranked, with lib + path). Combined with the annotations covering safety, nothing an agent needs to invoke and consume this tool is absent.

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 both the lib enum and the query field, including the AND-match rule. The description adds no extra syntax or format guidance for the parameters, so the baseline 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?

States a specific verb (search) plus the exact resource scope (current docs for ten named libraries), which immediately separates it from get_page_content and get_example. An agent can identify the tool's domain without reading the 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?

Explicitly says to call this FIRST before answering any question about these libraries, and gives the reason (docs track current releases newer than training data, APIs broke across major versions). It also names the downstream sibling: results carry a lib and path to pass to get_page_content.

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