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

Annotations already cover readOnly, idempotent and closed-world, so the bar is met; the description still adds real behavioral context by disclosing that the output is plain text with values substituted in, and that the numbers are the values at save time rather than today's. That snapshot-vs-current caveat is exactly the kind of fact an agent cannot get from the schema. It does not mention permissions or failure modes for a missing review_id.

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 entire definition is a single run-on sentence enumerating every returned field, which is dense and hard to scan; the key fact (what this call is and the saved-vs-today caveat) is buried mid-sentence and at the very end. The content is largely useful given there is no output schema, but it would benefit from being split and front-loaded.

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?

With no output schema, the description carries the full burden of describing the return shape, and it does so thoroughly, down to the fields held by the evidence and the review data it was derived from. Combined with annotations covering safety, an agent has enough to call it correctly. Only the routing guidance relative to similar review siblings is thin.

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 100%, so both the project scoping rule and the review_id source (list_reviews) are already documented in structured form. The description adds no syntax, format or provenance detail for the parameters beyond referencing recommendation ids in the return payload. Baseline 3 applies when the schema does the work.

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 states precisely what is returned: one saved AI review in full, with its enumerated sections (scope, period, short answer, confidence, recommendations, status, method, evidence). This distinguishes it from list_reviews and from the data-oriented get_review_data/get_review_follow_up siblings. The retrieval verb is only implied by 'One saved AI review in full' rather than stated outright, which keeps it just short of a 5.

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?

There is no explicit when-to-use statement or exclusion versus siblings such as get_review_data, get_review_follow_up or list_reviews. The one workflow hint is the parenthetical noting that a recommendation id can be passed to update_review, which implies the ids surfaced here are the inputs for that mutation. Usage is inferable but not guided.

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