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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds genuinely new behavioral context: access scoping ('accessible'), the presence of collection date and links in the response, and a prompt-injection warning that customer text must not drive tool actions. That last point is a real operational constraint not captured anywhere in the structured fields.

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?

Two sentences, no filler, and the functional statement is front-loaded before the security caveat. Every clause carries information an agent can act on.

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 usefully sketches the return (collection date, safe links), but it omits what happens on an inaccessible or nonexistent reviewId and where IDs come from. For a simple one-parameter read tool this is adequate, though not fully closed.

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 single reviewId parameter has no schema description (0% coverage), and the description only gestures at it via 'accessible review' — implying the ID must reference a record the caller can see. It adds no format, sourcing, or failure-mode detail beyond that, which is a modest gain over an undocumented schema field.

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 uses a specific verb (fetch) with a bounded resource ('one accessible review') and names the returned payload (collection date, source/dashboard links), so an agent can distinguish it from list/search siblings. It stops short of naming those siblings explicitly, so differentiation is inferred rather than stated.

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?

'Fetch one accessible review' implies the tool is for single-record retrieval by ID, which contrasts with the bulk sibling search_reviews. However, there is no explicit when-to-use/when-not statement and no guidance on how to obtain a valid reviewId (e.g., from search results), leaving the workflow context implied.

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