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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It reveals determinism ('No LLM is involved'), caching behavior ('cached by SHA-256, so repeat calls are instant'), page-number semantics, and the need to check review.required and warnings before trusting a degraded map. This is substantial, non-obvious behavioral context.

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?

Though lengthy, the description is dense and every sentence earns its place. The core definition is front-loaded, followed immediately by usage priority, exclusion guidance, page-number semantics, and trust caveats. There is no filler, repetition, or vague prose.

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 lacking an output schema, the description names the key return elements an agent must use: anatomy.dominant_form for tool selection, review.required, warnings, and the per-page geometry census. It also explains the cache behavior and physical page numbering. For a one-parameter tool, this is complete enough to call and use 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?

There is only one parameter, documentPath, and the schema description already defines it as an absolute filesystem path or https URL. The tool description adds that it is a datasheet PDF, which is consistent but not materially new information. With 100% schema coverage, the baseline 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 clearly states a specific verb and resource: 'Build the Document Map of a datasheet PDF.' It enumerates the map's contents (topic locations, page physical forms, geometry census) and explicitly differentiates itself from a sibling by saying 'use extract_pinout for pins.' An agent cannot confuse this with the other 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?

It gives explicit when-to-use guidance ('USE IT FIRST, before reading any page of a datasheet'), what to do next with the map ('read the candidate pages it recommends and pick your tool per page from anatomy.dominant_form'), and what not to use it for ('Do NOT use it to get pin names, dimensions, or ratings'). It even names the alternative tool for pins.

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