pmndrs docs

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

Annotations already declare readOnly/openWorld=false/idempotent/non-destructive, so the safety profile is fully covered. The description adds genuine value by describing the shape of the payload (demonstration summary, targeted versions, full source files), which matters because there is no output schema.

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 the core action before routing guidance. No filler; each clause 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?

Despite no output schema, the description explains the return contents, gives the required parameter source, and routes to alternatives. An agent has everything needed to select and invoke 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 description coverage is 100% and the description's only mention of `name` ('Take `name` verbatim from the examples://index resource') simply repeats what the schema already says. Baseline 3 applies since the schema carries the 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?

States a specific verb and resource ('Read one pmndrs example in full') and then enumerates exactly what is returned: what it demonstrates, the versions it targets, and every source file. This clearly separates it from get_page_content and search_docs.

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 states when to reach for this tool ('when the question is how a scene is put together') and names the alternatives for a different need ('for what an API takes, search_docs then get_page_content'). Both the when and the when-not are covered with named 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, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds non-obvious behavioral context instead of repeating it: paths are matched exactly, their shape varies per library, and guessing is prohibited. It does not discuss rate limits or failure modes, so 4 rather than 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 sentences, front-loaded with the action, then the sourcing rule, then the fallback instruction. No filler and nothing repeated from the schema.

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?

A read-only, two-parameter tool with full annotation coverage, a 100%-documented schema, and a description that even states the return form ('as current markdown'). Nothing an agent needs to call 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 value beyond the schema: both arguments must be copied verbatim from a search_docs hit, and paths are exact-matched with library-specific shapes. That is guidance the schema does not provide.

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'), making it immediately distinguishable from the sibling search_docs, which returns hits rather than a full page. An agent can tell which tool fetches content versus which one discovers it.

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,' and tells it where to source the arguments ('Take lib and path verbatim from a search_docs hit'). The when-to-use and the alternative are both named, 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 readOnly, idempotent, non-destructive and openWorld=false, so the safety profile is covered. The description adds real behavioral context beyond that: result cardinality (10), ranking (best first), and the fields each result carries, plus the staleness rationale. It stops short of anything like filtering/collision behavior or failure modes, so 4 rather than 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 sentences, front-loaded with the search purpose, then the when-to-use imperative, then the return shape. The version-break detail is dense but each clause justifies itself by explaining why an agent should not rely on memory.

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 still specifies the return contract (10 ranked results, each with lib and path, feeding get_page_content). Combined with the full input schema and annotation coverage, an agent has everything needed to call it correctly first in a docs workflow.

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 already documents both parameters well, including the lib enum and the 'every term has to match' semantics of query. The description adds only indirect value (naming the libs searched, referencing the lib/path output), so the baseline 3 is correct.

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 precise resource scope: the current documentation of nine named libraries. An agent immediately knows what corpus is searched and that results are the 10 best-matching pages, distinguishing it from get_page_content and get_example.

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?

Explicit routing instruction: 'Call this FIRST, before answering any question about one of these libraries,' with the reason given (docs track newer releases than training data; APIs broke across major versions). It also names the follow-up step, telling the agent results carry the '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.