Judge a price against the market

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

Annotations declare readOnlyHint=true and openWorldHint=true, and the description adds significant behavioral context beyond that: it clarifies these are ACTIVE ASKING PRICES, not sale prices, warns that Leboncoin publishes no transaction data, and instructs the agent to phrase outputs as 'des annonces similaires sont à environ 90 €' rather than 'ça se vend 90 €'. It even explains why asking prices skew high (unsold items stay listed, sold ones vanish). This is legitimate behavioral disclosure not present in annotations. A 4 is fair since the read-only nature was already disclosed by annotations, but the description does add substantial semantic and honesty constraints.

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 description is a single dense paragraph that packs a lot of value without waste. Every sentence earns its place: the core purpose, the exact output categories, the when-to-use guidance, the sibling alternative, the key semantic distinction (asking vs sale), and the user-facing language instruction. It is front-loaded with the purpose and the actionable output, followed by the caveats.

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 the tool's moderate complexity (25 params but high schema coverage, no output schema, read-only annotations), the description covers the key context an agent needs: what the tool does, what the outputs mean, how to phrase results for the user, and why the data is the way it is. It could arguably mention the percentile return more explicitly, but overall it is fairly complete for its complexity. A 4 is justified because it covers the important interpretive pitfalls without being exhaustive.

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 high at 88%, so the baseline is 3. The description adds meaning for targetPrice and listingId implicitly by stating 'the user's asking price, or an ad you are looking at' and the schema says targetPrice is 'The price to judge. Required unless listingId is given.' The purpose text helps the agent understand the relationship between the judgment and the comparables, but most parameter semantics are already well covered by the schema. The description does not add much beyond what the schema provides.

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+resource combination: 'Places a price you already have... inside the distribution of comparable active listings' and explicitly names the five output verdicts (well_below, below, fair, above, well_above) plus percentile. It also distinguishes itself from its sibling estimate_price ('For "what should I ask?", use estimate_price instead.'), which clearly separates this judging tool from the pricing tool.

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 description gives explicit guidance on when to use this tool: 'Use it to answer "is this a good deal?" or "is my price reasonable?".' It also provides an explicit alternative: 'For "what should I ask?", use estimate_price instead.' This is exactly the kind of when/when-not guidance that helps an agent choose correctly between siblings.

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