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

Annotations already establish read-only and idempotent traits with readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description goes beyond this by explaining the data model quirk: attribute_keys are shared with get_category, and attribute_labels contains display vs raw values, which is important for correct downstream formatting. The explicit 'Only public listings can be fetched' discloses a major behavioral limitation not captured in annotations.

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 four sentences, each one carrying meaningful information: the core purpose, the attribute-key relationship, the raw-vs-label distinction for presentation, and the public-only restriction. Though a bit longer than minimal, there is no filler—every paragraph earns its place. It maintains a logical flow from purpose to details.

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?

There is no output schema, so the description does the heavy lifting of communicating the response contents (description, price, location, category, attributes, labels). It also clarifies the critical relationship with get_category, which helps the agent understand attribute keys. It stops short of fully specifying the response shape or error behavior for private/not-found listings, which a more complete description would include.

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?

With only one parameter, listingId, and schema description coverage at 100%, the schema already fully documents the parameter ('Numeric listing id, as returned by search_listings'). The tool description doesn't add anything of additional semantic value beyond repeating that it is a listing ID. Following the baseline rule for high schema coverage, a score of 3 is appropriate.

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 operation 'Fetch one published listing by id' and enumerates the included data fields (description, price, location, category, attributes). This clearly distinguishes it from siblings: search_listings returns multiple listings, get_category returns category metadata, and get_category_names returns category names. An agent can categorize the tool without inspecting other schemas.

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 communicates the tool's scope (single listing lookup by ID) and a key constraint ('Only public listings can be fetched'), which implies when the tool would be invalid (private listings). However, it does not explicitly mention when to use search_listings instead (e.g., when searching without an ID) or when additional attribute context would require get_category. These exclusions are not explicit enough for a perfect score.

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