manage_chat

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

Annotations declare the safety profile (not read-only, not destructive, not idempotent, open-world), so the description doesn't need to restate it. It adds a couple of genuine behavior facts — the 3-pin cap and mute's default of 'forever' — but says nothing about permissions, reversibility, or partial-failure behavior across the ten distinct actions.

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 summary sentence followed by a compact action table; every line maps to a real enum value and earns its place. Slightly longer than strictly necessary given the schema already enumerates the actions, but the pairing of action-to-meaning is efficient.

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 5-parameter dispatcher with no output schema and full schema coverage, the description covers all action semantics and the key per-action constraints. Missing only cross-cutting details like auth/session routing for target_session and what happens on invalid action/parameter combinations.

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 description coverage is 100%, and the two enums (action, mute_duration) are fully documented in the schema, so the baseline is 3. The description's per-action lines add only marginal meaning beyond the schema, mostly repeating the conditional requirements already stated in parameter descriptions.

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?

The description states a clear verb+resource ('Manage chat state') and then enumerates all ten concrete actions, so an agent knows exactly what surface this tool covers. It does not, however, distinguish itself from any sibling tool — though none of the listed siblings appear to overlap with chat-state mutation.

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?

Per-action annotations give useful constraints ('max 3 pinned', mute uses mute_duration, set_draft requires text), which is real usage guidance. But there is no statement of when to reach for this tool versus alternatives, nor any preconditions or failure conditions.

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