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

The readOnlyHint annotation already signals the operation is non-mutating, and the description adds valuable context by explaining that return includes the written review text, not just the average, and enumerates the fields each rating carries. It also clarifies that direction 'given' changes the perspective from received to left ratings. The description does not mention pagination, ordering, or rate limits, but for a read-only tool with this clarity that is a minor gap.

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 long and each one serves a distinct purpose: scope, how to query by username, how to query by job, and what the output contains. It is front-loaded with the read intent and the contrast to the average, then it gives operating instructions. No unnecessary words or repetition are present.

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?

The description fully explains the parameters, the mutual exclusivity, the default direction setting, and the output fields, which compensates for the absence of an output schema. It lacks explicit mention of ordering or pagination behavior for a user with many ratings, but these are not necessary for an agent to invoke the tool correctly in most cases. Overall, the description is sufficiently complete for a read-only three-parameter tool.

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?

Even though the schema descriptions already cover 100% of the 3 parameters, the description adds meaning beyond them: it explains the default behavior of direction ('received'), defines exactly how username and job_id are mutually exclusive, and gives semantic context like 'the ones they left instead' and 'both ratings on a single job'. It also states that exactly one of username or job_id is required, which the schema alone does not enforce.

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 'Read individual ratings, including the written review text', which precisely names the verb and resource while distinguishing this from the inline average shown elsewhere. It also explicitly contrasts itself with the aggregated 'average that job results inline', making the tool's unique purpose unmistakable.

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 clear, explicit instructions for all modes: pass username for ratings received, add direction 'given' for ratings left, or pass job_id for both ratings on one job. It clearly states the mutual exclusivity requirement. However, it does not explicitly mention alternative sibling tools or conditions where a different tool should be chosen instead.

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