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

Annotations already cover readOnly/idempotent/openWorld, and the description still adds materially: the negative-result caveat ("No record means apiwatch has no record for it, not that it is safe") and the scoping caveat that some records apply only in certain repos or files. These are exactly the interpretive details an agent would otherwise get wrong.

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 purpose and then usage timing, with no filler. The return-value sentence is a dense enumeration that partly duplicates the output schema, which keeps it from a 5.

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 single-parameter read tool the description is complete: purpose, timing, result shape, negative-result interpretation, and scope caveats are all present, and annotations cover the safety profile. An agent has everything needed to call it and interpret results.

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 parameter already says "The model id as it appears in code", so the schema does the heavy lifting. The description adds concrete format examples ("gpt-4o-2024-05-13", "claude-sonnet-4-5") that help the agent format the value correctly, which is a modest but real gain over baseline.

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 precise verb and resource ("look up one AI model id") within a named corpus ("apiwatch's reviewed feed of vendor changes") and gives two concrete id examples. The single-record lookup scope clearly separates it from siblings like search_changes or list_upcoming.

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?

"before you use it in code" gives an explicit usage moment, which is more than most descriptions offer. It stops short of naming alternatives (e.g. check_identifiers for non-model ids) or stating when not to use it, so it falls short of a 5.

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