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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered and 'Read-only' merely restates it. The description earns credit elsewhere: 'It quotes nothing at any tier' discloses that no message content is returned (a real behavioral trait an agent must know before citing), and the refusal condition names a concrete failure mode. Pagination/limits are not mentioned, which keeps it from a 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?

The response shape is front-loaded in the first sentence and the actionable follow-up comes immediately after, so an agent gets value in the first few words. Two sentences with no filler, though the metaphor-laden phrasing ('which way it ran') costs a little decoding compared with plain terms like 'direction'.

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 an output schema present, the description need not describe return values, and it correctly focuses on purpose, the no-content guarantee, the refusal condition, and the next step. The main hole is parameter meaning for a nested 3-param tool, but overall an agent could invoke this correctly from what is given.

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 a middling 67%, and `agentName` has no description at all. The description contributes nothing about any of the three parameters — no meaning for `threadId` vs `companyId`, no mention of what `agentName` filters or defaults to. All semantic burden falls on 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?

The description concretely enumerates what the timeline contains: each exchange, when it ran, message counts, participants, and direction — an agent can predict the shape of the response. The framing metaphor 'The shape of a chat thread' is evocative but the content that follows is specific. It stops short of distinguishing itself explicitly from `fundraising_list_chat_threads` or `fundraising_map_chat_thread`, which is the main residual gap.

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?

'Read it to find the exchange worth citing, then cite one message by id with IngestChatEvidence' gives an explicit workflow and names the follow-up sibling tool, which is strong routing guidance. It also supplies an exclusion — 'Refused only on a thread the founder stopped' — telling the agent when it will not work. It does not compare against other thread-inspection siblings, so it is not quite a 5.

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