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

With no annotations, the description carries the full burden and does so well: organizer-only auth, that true replaces the session's existing pin and may surface on the main screen, that false merely unpins and does not hide, that hidden messages cannot be pinned, that there is no restore path, that repeated pinning rewrites the timestamp (non-idempotent), and that unknown failures must be verified in the host console with no automatic retry. These are exactly the mutation risks an agent needs. It stops short of describing the response payload or what happens to the previously pinned message's state after replacement.

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 auth/scope condition, then prerequisites, then flag semantics, then failure handling. Semicolon-delimited clauses carry no filler; every clause adds an operational constraint.

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 four-required-parameter mutation with no output schema and no annotations, the description covers authorization, pre-read verification, both flag branches, state side effects, irreversibility, non-idempotency, and retry policy. There is no material gap an agent would need to close before calling it.

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 schema already documents all four parameters and baseline would be 3. The description goes beyond it by attaching consequences to the pinned flag that the schema does not state: true may put the message on the main screen, false is unpin-only and does not hide, plus the requirement to verify messageId provenance via get_organizer_live.

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 pair (pin/unpin) on a specific resource (this live session's interactive message) and scopes it to '本场' (this session). The agent can distinguish it from hide_live_message and post_live_message purely from this sentence.

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 prescribes the prerequisite workflow (call get_organizer_live first to verify author, messageId and full text, and confirm pinned plus scope with the user) and spells out when to pass true versus false. It also states a hard exclusion: hidden messages cannot be pinned, which routes the agent away from this tool in that case.

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