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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real behavior: newest-first ordering, a next_search-based pagination mechanism, the constraint that a channel outside this Agent matches nothing, and a prompt-injection warning that transcript text is untrusted. It does not mention rate limits, result caps, or match-quality behavior (e.g., fuzzy vs. exact), which keeps it below 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?

Roughly five short sentences with the core scope front-loaded and the safety caveat placed last where it is likely to be read. Every clause carries information; the only mild awkwardness is mixing a response field (next_search) into the parameter narrative.

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, return values need no explanation, and the description covers ordering, pagination, scoping, filters, and injection safety for a two-parameter nested-query tool. What remains thin is how matching works and whether results are capped, which matters for a search tool.

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 100%, so baseline is 3, but the description adds meaning the schema lacks: query matches contact names and message text, and channel_id is scoped to the given Agent so foreign channels yield nothing. It skips explaining before/before_id directly, routing pagination through next_search instead, which is helpful but leaves the cursor pair undocumented in prose.

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 ('searches one Agent's whole conversation history') plus a meaningful scope and sort order ('newest activity first'), which sets it apart from generic inbox tools. It never names a sibling such as inbox_messages or agent_channel_activity_read, so differentiation is left to inference.

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?

Usage context is implied by the scope ('one Agent's whole conversation history') and the filter list, so an agent can infer this is the history-recall tool. There is no explicit when-to-use vs. when-not guidance or named alternative, and no statement about what to do if the agent_id is unknown beyond the schema note.

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