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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint, non-destructive), but the description adds genuinely new operational facts: a 2¢ per-call cost and the shape of the return ('matching chunks with part_number and a 0-100 relevance_score'). It does not discuss empty-result behavior or how limit affects result quality, which keeps it short of 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?

Four short sentences, all front-loaded: cost first, then scope, then return shape, then the alternative. Every sentence carries a distinct fact and none restates the name or title.

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?

There is no output schema, yet the description still supplies the return shape and relevance scale, plus corpus scope, cost, and the disambiguation rule. An agent has everything needed to decide between this and search_parts and to interpret the response.

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 baseline is 3, but the description adds real meaning for the required query parameter by showing the expected style (spec-based natural-language phrase rather than a part number). The limit and section_type parameters are left entirely to the schema.

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 (semantic search) and resource (extracted datasheets) and immediately bounds the corpus with 'not every part that exists'. It also names the sibling it is not: search_parts for lookup by part number, so an agent can distinguish it without opening either 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 the positive trigger with a concrete example ('low-noise LDO with PSRR above 70dB') and an explicit when-not rule routing part-number lookups to search_parts. Both the condition and the alternative are named, leaving nothing to inference.

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