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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint=false, so restating 'Read-only' earns nothing. The description does add real behavioral context the annotations cannot: that it covers all non-stopped threads across every connected source and returns derived state like 'counterparty wrote last / founder owes a reply'. It says nothing about pagination, ordering, result caps, or auth scope, which are the remaining unknowns for a list endpoint.

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-loaded with the core object ('The founder's chat inbox over every thread...') followed by a single dense enumeration of returned fields, then the citation caveat. No filler sentences, though the field enumeration is a long run-on that could be trimmed given an output schema already exists.

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, re-listing every returned field is partly redundant, while the genuinely missing pieces — how the label/agentName/needsReplyOnly params behave and whether results are paginated — go unaddressed. Adequate for an agent to know what it gets back, not adequate to steer the optional parameters correctly.

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 25% and only companyId has a (trivial) description, so the description must carry weight. It implicitly explains two of the four params by mentioning 'the founder's labels' and 'whether the counterparty wrote last (the founder owes a reply)', but never frames them as filters, and the agentName parameter is entirely unaddressed in both schema and description.

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 names a concrete resource (the founder's chat inbox across connected chat sources) and enumerates exactly what each thread row carries: counterparty, participants, mapped relationship, last-activity, reply-owed flag, labels, and unmapped threads. That is far more specific than a restatement of the title. It stops short of 5 because it never distinguishes itself from the very close sibling fundraising_list_chat_threads, leaving an agent to guess which listing to call.

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 gives one explicit exclusion plus the alternative: the tool quotes no message text, so message bodies must be cited via IngestChatEvidence. It also scopes the read to threads the founder has not stopped. What is missing is any when-to-use guidance against list_chat_threads or map_chat_thread, so routing for the main ambiguity is left to inference.

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