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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the bar is lower. The description still adds real context: the 2-5 measure limit (not encoded in the schema, which has no minItems/maxItems) and the shape of the aligned result (goal scores, retention, cooling, infiltration, costs, maintenance, scale).

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 one-line purpose followed by a compact args section and a short returns line, with no filler. The Python-docstring formatting is slightly noisy but each line carries information.

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 with an output schema, the definition covers input format, valid-value discovery, and expected comparison dimensions. It stops short of error behavior or how results are ordered, which is minor given the output schema exists.

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 0%, so the description must carry the parameter meaning, and it does: measure_slugs is a list of 2-5 slugs, with a concrete example and a pointer to search_bgi_measures for valid values. The only gap is that it does not say what happens with duplicate or invalid slugs.

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?

"Side-by-side comparison of 2-5 BGI measures" names a specific verb (compare) and resource (BGI measures) with an explicit arity bound. It does not distinguish itself from the closest sibling, rank_measures, so an agent must infer when to compare versus when to rank.

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?

The definition gives a useful prerequisite: use search_bgi_measures to find valid slugs, which prevents a common failure mode. However it never states when to use this over rank_measures or get_measure_detail, so the choice among the three measure-oriented siblings is left to inference.

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