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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, and the description adds real value beyond them: the return ordering and field set (who, last message, time, unread) and the auth requirement ('Needs the user's Cotlet API key with access to this app'). It does not mention rate limits or pagination semantics beyond what the cursor schema implies, keeping it at a solid 4 rather than 5.

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?

Front-loads the resource and purpose well, with routing guidance last. The opening fragment ('Your Messages inbox: who, last message, time...') largely duplicates the following sentence's field list, so a small amount of redundancy costs it the top score.

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 a read-only annotation set and no output schema, the description carries the return-shape burden and does so (fields and ordering), plus the auth prerequisite. It is complete enough for a simple, filterable list tool, though pagination behavior via cursor is only implied by the 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 limit and cursor are fully documented in structured data. The description only lightly reframes unread_only ('see only what needs an answer'), which is close to the schema's own text, so the baseline 3 applies.

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+resource ('Lists your Dribbble Messages conversations') and enumerates the concrete return fields (other person, last message preview, time, unread flag) plus ordering ('most recent first'). Naming get_conversation and reply_to_message as downstream siblings makes the list-vs-fetch-vs-reply boundary clear without opening a schema.

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 conditions: 'Set unread_only to see only what needs an answer' and 'Pass conversation_id to get_conversation or reply_to_message', which routes the agent to the correct follow-up tools. It stops short of an explicit when-not-to-use-this-tool statement, so it sits just below the top tier.

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