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

Annotations already establish the read-only, open-world, non-destructive profile, and the description usefully adds the sort order, page size (up to 100), the cursor chaining behavior, and the auth requirement ('Cotlet API key with access to this app'). This is real added context beyond the annotations, though return shape detail is still thin.

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?

It is front-loaded and reasonably short, but the opening 'Clients with contact details and tags, newest first' and the following 'Lists the clients on your account, newest first' repeat the same sorting fact, wasting a sentence. Trimming the redundancy would tighten it without losing information.

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 four-parameter list tool with no output schema, the description covers sort order, page size, pagination chaining, filtering, and auth requirements, which is sufficient for correct invocation. Only the exact returned fields remain unspecified, which is acceptable given no output schema.

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 all four parameters are already documented, setting a baseline of 3. The description mostly restates this (tag example, name/email, cursor reuse, 100-per-page), adding the 'spring' tag example and pagination flow but little semantic 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 and resource ('Lists the clients on your account') with scope ('newest first') and content ('contact details and tags'). It is clearly a list operation distinguishable by name and behavior from thryv_get_client and thryv_add_client, but it never explicitly contrasts itself with those siblings.

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?

It explains how to use the filters ('Filter by name, email or tag to find a group such as everyone tagged "spring"') and the pagination flow, which is useful usage context. However, it gives no explicit when-to-use-this-vs-alternatives guidance and no exclusions, so usage remains implied.

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