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

Annotations cover safety (readOnly, idempotent, non-destructive, openWorld), and the description adds operational traits well beyond them: no files needed, sources consulted (IA plus five manufacturers), latency ('up to about two minutes when the archive is slow'), a hard coverage limit ('only revisions captured by the Internet Archive can be found'), validation evidence, and an honest untested case (a real pair with an actual value change).

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?

Front-loaded with the usage trigger and key constraint, and every sentence carries information (scope, sources, returned fields, limits, validation). It is somewhat dense and the validation statistics are closer to trust marketing than operational guidance, but nothing is truly wasted.

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 an output schema existing, the description specifies exactly which parameters are reported (VDS, ID, VGS, RDS(on), VTH, QG, RthJC, TJ max with min/typ/max, conditions, page/quote) and the revision list, plus runtime, coverage limits and refusal behavior. An agent has everything needed to call it and set expectations.

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 clarifies the default comparison behavior (newest revision vs. previous one) and the role of 'since' (compare against the revision valid then), which is meaning beyond the bare property 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 (find and compare MOSFET datasheet revisions) and names the exact input (part number only, no files). It also scopes out adjacent artifacts (IGBTs, modules, diodes) and the sibling activity it replaces (searching the web yourself), so an agent can place it without opening 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?

Explicit trigger ('when the user asks whether the datasheet of a discrete MOSFET changed, e.g. after a PCN, a last-time-buy notice or before reusing a part'), explicit preference over the alternative ('Prefer it over searching the web yourself'), and explicit exclusions with an error code ('IGBTs, modules and diodes are refused with OUT_OF_SCOPE').

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