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

Annotations only declare readOnlyHint and openWorldHint, but the description adds materially: cost (10 credits), the Alsace/dept 67-68 zero-result limitation, the 200m nearest-DPE matching caveat that class gaps are indicative, and the data-coverage limitation pointers for prime_verte. These are real behavioral traits an agent needs and are not in the structured fields.

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-loads the one-line purpose, then structures detail into numbered analyses, a when-to-use block, param requirements, and caveats. Slightly long and the numbering (1, 2 then 3) is a bit uneven, but nearly every line carries information the caller needs for a multi-output analytical tool.

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?

Given no output schema, the description fully explains the return shape (two distinct analyses, threshold/coverage metric, sieve share with annual trend), the constraints, the data limitations, and the cost. Nothing essential for correct invocation or interpretation appears missing.

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 per-parameter descriptions are already present. However, the schema lists 0 required parameters, while the description supplies the true constraint ('REQUIRED: at least one location — code_postal, commune, or code_departement'), which is a meaningful addition the schema does not encode. It also clarifies the Maison|Appartement option but adds little else beyond schema syntax.

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+resource ('Combined DPE market analysis — price per energy class AND thermal sieve stock') and enumerates exactly what the three returned analyses are. It also names and contrasts with the closest sibling, analyze_dpe_price_premium, so an agent can distinguish them without opening any 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?

Has an explicit 'WHEN TO USE THIS vs analyze_dpe_price_premium' block that gives the selection condition for each ('full DPE snapshot' vs 'how much more is an A vs the local median'). This is textbook when-to-use/when-to-use-the-alternative guidance.

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