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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description only needs to add behavioural context — and it does, clarifying the message mix returned and the delta-fetch semantics of since. It says nothing about ordering, limits, or what happens with an invalid since value.

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, front-loaded with the purpose and finishing with the one operational hint. No filler or restated title.

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 tool with no output schema and only three parameters, the description covers what the thread contains and how to page through it. Missing output shape, ordering, and pagination limits are tolerable given the readOnly annotations, but would have made it complete.

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 only 33% (only token is documented). The description meaningfully explains `since` as a last-seen message_id cursor, which is exactly the kind of detail the schema lacks, but rfq_id remains undocumented in both places. It partially compensates rather than fully.

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 ("Read the conversation of a request") and enumerates the content returned — factory answers, quotes, files, and the caller's own messages. That is enough to distinguish it from get_rfq (metadata) and send_rfq_message (write), though it never names those siblings explicitly.

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 a concrete usage pattern: pass since=<last message_id> to fetch only new messages, which tells the agent this is the incremental-polling path after an initial read. It does not state when to prefer get_rfq/get_request instead, so there is a small gap, but useful context is present.

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