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 real context beyond that: it discloses what the answer contains (oven temperature, resting time, pull-out temperature, a tip) and conditional behavior such as shoulder cuts being slow roasted and gammon being roastable or simmerable. It does not mention units handling edge cases or output formatting, but the conditional branches are genuinely useful.

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?

The purpose and weight-based framing are front-loaded, and the sentence about serve_time is a useful closer. The middle clause repeating per-meat doneness levels duplicates the schema and could be trimmed without losing information. Dense but mostly earning its space.

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 six parameters, no output schema, and 83% schema coverage, the description correctly compensates by explaining the shape of the returned answer (temperature, resting time, pull-out temp, tip, oven-in time). The main remaining gap is the absence of any mention of how it relates to plan_roast_dinner or turkey_cooking_time. For a read-only lookup tool this is close to complete.

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 83%, so the schema already documents cut, unit, doneness, weight and serve_time thoroughly. The description largely restates the doneness and cut options rather than adding syntax, though it does add one piece of meaning not in the schema: that lamb and pork shoulder are slow roasted, which explains why cut changes the result. Baseline 3 is appropriate given the schema carries most of the load.

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 opens with a specific verb-and-resource framing: how long to roast which meats, by weight, with oven temperature and resting time. The enumerated meat list (beef, lamb, pork, chicken, gammon) implicitly excludes turkey, which is the sibling tool turkey_cooking_time, so an agent can infer the split. It stops short of naming that sibling explicitly, which keeps it from a 5.

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?

Usage is only implied through the meat/cut/doneness enumeration; there is no explicit when-to-use-this-vs-sibling statement and no prerequisites or exclusions. The one concrete usage instruction, 'Give a serving time to get when it goes in,' tells the agent how to use serve_time but not when the tool itself is the right choice. Adequate but leaves routing to inference.

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