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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is set. The description adds genuine context beyond that: it requires the Cotlet API key with access to the app, and aggregates reviews across all connected sites (explaining the open-world reach).

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 opening two sentences are near-verbatim duplicates ('Reviews from the Reputation dashboard...' vs 'Lists reviews from the Reputation dashboard...'), which is wasted space. The remaining guidance and auth note are efficient and useful, but the redundancy blunts the structure.

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?

For a read-only list tool with no output schema, the description covers what comes back (reviews with rating, text, replied flag), the aggregation scope, the auth requirement, and the follow-up path to reply_to_review. Sufficient for correct invocation, though pagination or return shape is not addressed.

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 coverage is 100%, so both parameters (since, unanswered_only) are already documented, making the baseline 3. The description reframes unanswered_only in outcome terms ('see what needs a reply') and mentions review_id as a value that flows into reply_to_review, but adds little mechanical detail beyond the schema.

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?

States a specific verb (lists) and resource (reviews) with scope (Reputation dashboard, every connected site) and returned fields (rating, text, replied). It implicitly distinguishes itself from the sibling reply_to_review by pointing there, though the first two sentences restate the same purpose and dilute the sharpness.

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?

Gives actionable routing: 'Use unanswered_only to see what needs a reply' and 'Pass review_id to reply_to_review', which names the follow-up sibling and the condition for using it. It does not state when to use this listing versus other Thryv list tools, but the key usage paths are covered.

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