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

Annotations only declare the safe-read profile; the description adds real behavioral context beyond that: suppressed pairs and the chat's own row are excluded, rows carry link_version for a later link call, and output ordering differs by mode. It also flags that names and message text are untrusted customer content that must never be treated as instructions.

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?

Information is front-loaded: scope first, then mode behavior, then exclusions, then the untrusted-content warning. The prose is dense and slightly clause-heavy but nearly every sentence carries distinct signal.

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 explain return values, and it nonetheless covers ordering, exclusions, the link_version handoff, and prompt-injection risk. Nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description adds meaning the schema does not convey: setting q changes the entire result shape by suppressing the likely block, and it frames q as the user's own words rather than a suggestion. The chat_id @lid constraint is largely a restatement of 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?

"Contact picker for one hidden-number chat (id ending in @lid)" gives a specific verb, resource, and scope, and the q/no-q split further pins down the two modes. It is clearly separable from siblings like search_contacts, get_chat_identity, and list_identity_changes without opening any 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?

It states concretely when to omit q (to get likely matches ranked by evidence kind and weight) versus when to pass q (a plain search with no likely block), plus the caveat that likely matches are hints, not answers. It does not name a specific alternative sibling tool to use instead, which keeps it just short of a 5.

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