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

Without annotations, the description takes on the full burden. It discloses that the tool captures changes that 'exists nowhere upstream' because providers overwrite their catalogue, and it reveals input clamping ('days is clamped to 7') and row capping ('more than 25 rows — it is capped'). However, it does not explicitly state whether the operation is read-only or if there are any side effects, though it is implied as a data query tool.

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 paragraph that is somewhat conversational but logically structured: it starts with the tool's output, explains its unique value, gives usage guidance, and ends with constraints. It is not overly verbose and each sentence adds information, though it could be slightly more compact.

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 simplicity and lack of an output schema, the description covers all essential aspects: what it does, why it exists (to capture data not available upstream), when to use it, and its limitations. It does not discuss error handling or output format, but these are not critical for a simple query tool and the information provided is sufficient for an agent to use it correctly.

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?

The schema provides no parameter descriptions, so the description is the only source. It mentions 'Input: days is clamped to 7' and refers to 'windows longer than 7 days' and 'more than 25 rows', giving some meaning to `days` and `limit`. However, it does not directly define each parameter's purpose or expected values in a structured way, leaving some ambiguity.

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 clearly states that the tool provides LLM price changes observed in the last 7 days, detailing what fields are returned (per model, field moved, from/to values, percentage, timestamp). It also explicitly states the use case: 'Use it to detect that a model you depend on got cheaper, dearer, or vanished.' This distinguishes it from siblings by noting its limitation and pointing to the paid alternative for full history.

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 explicitly says when to use the tool ('Use it to detect...') and when not to use it ('Do NOT use it for windows longer than 7 days or more than 25 rows'). It also gives a clear alternative ('use anansi_price_changes (paid) for the full unwindowed history') and notes that the input 'days is clamped to 7', setting expectations for usage constraints.

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