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

Adds real context beyond annotations: requires login, TA is not notified, and TA's profile page remains visible — side-effect and visibility facts annotations cannot express. It is consistent with idempotentHint=true and destructiveHint=false (the toggle is reversible). It stops short of, e.g., clarifying effects on direct messages or other surfaces, so not a full 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?

Two compact, bracket-labeled sentences: effect first, then combination/routing guidance. Every clause carries information — no filler or restatement of the name.

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 a login-gated, non-destructive, idempotent toggle with an output-schema-less response and fully documented params, the description covers prerequisite, both parameter states, side effects, and alternatives. Nothing needed to call it 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 consequence-level meaning for the boolean (true hides TA's posts from the feed without notifying TA; false restores), which goes beyond the schema's terse 'true 不看 TA | false 恢复看'.

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?

Names a specific verb+resource: toggling whether 'TA' appears in my moments feed (set_moment_mute). It clearly distinguishes itself from sibling block_user by scoping the effect to the feed rather than a full disconnect, so an agent can differentiate without opening the 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?

Explicitly states both directions of use (muted=true to stop seeing, muted=false to restore) and names the two alternatives with the conditions that select them: use block_user for a full disconnect, or just skip a single post. This is textbook when/when-not guidance.

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