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

Annotations only supply destructive/idempotent/openWorld hints; the description goes well beyond them by disclosing atomic validation ('Everything is validated before anything changes'), the full-replacement semantics of `instructions`, the propagation delay ('the AI follows the new text on its next replies, usually within a minute'), the no-op behavior when the text is unchanged, and the `422 field_not_writable` contract with the offending field in `param`. That is the behavioral detail a mutation tool needs.

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 correctly: field list first, then validation/replacement behavior, then rejection rules, then sibling routing. Individual sentences are clause-heavy and slightly run-on, but every clause carries operational information and there is no filler.

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 an 8-parameter, no-output-schema mutation tool, the description supplies the missing pieces: error codes, atomicity, replacement semantics, propagation latency, and escape hatches to sibling tools. Nothing an agent needs to invoke this correctly is absent, and return formats are unnecessary given the absence of an output schema.

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 and the per-field mechanics (IANA format, clearing via empty string, length bounds) are already handled by the schema. The description earns the bump by explaining whole-text replacement for `instructions`, the no-op re-send case, and the fact that certain fields are rejected wholesale — semantics the schema's `additionalProperties: false` does not itself convey.

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?

Specific verb+resource (update an agent's settings) followed immediately by an exhaustive enumeration of the mutable surface: name, description, instructions, time zone, AI handoff, comment auto-hide. It also explicitly carves out what is *not* this tool — deletion lives in the dashboard, follow-ups in `updateFollowUpSettings`, per-channel AI switch in `updateConnection` — so the agent can separate it from every nearby sibling.

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?

States the precondition plainly ('Send at least one (`422 no_settings` otherwise)') and names the replacement tools for the adjacent concerns, which is exactly the when/when-not/alternative guidance an agent needs. The non-writable field list ('status', 'ai_model', 'model_provider', 'avatar_url', 'language') doubles as a do-not-attempt directive with the resulting error code.

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