call_tool

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

Adds substantial behavior beyond the annotations: the preview tick confirm guard for dangerous tools, the RFC 8693 token swap when team_sid is set, the requirement that the OAuth grant covers the target team and that the caller be a live member, and the meta.team_sid echo on every response. None of this is recoverable from readOnlyHint/idempotentHint alone.

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?

Three sentences, front-loaded with the core action and then the two exceptional paths (confirm flow, cross-team). It is dense and every clause carries information, though the final team_sid sentence is long enough that a reader must parse it carefully.

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 polymorphic dispatcher with no output schema, the description covers dispatch, the confirmation handshake, and cross-team auth, plus one concrete return detail (meta.team_sid). It does not describe error/denial behavior or how results of the invoked tool are surfaced, which is the remaining gap.

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 75%, and the description still adds real meaning: it explains where `name` must come from, that commit_token rides inside `arguments` on the confirm call, and the full semantics and preconditions of `team_sid` (token exchange, grant coverage, live membership, omit-for-default). Only `_meta.user_goal` is left to the schema, which documents it adequately.

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 and resource ('Invoke a tool by name') and immediately scopes it with the discovery prerequisite ('discovered via get_toolset_tools'), which cleanly separates it from both siblings. An agent can tell this is the dispatch/execution tool, not the discovery or listing tool, without opening a 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?

Gives a clear entry condition (name must come from get_toolset_tools) and the special flow for dangerous tools (two-step preview tick confirm with commit_token inside arguments). It also routes the cross-team case to team_sid. It never states when *not* to use it, but the prerequisites are explicit enough that an agent will not misfire.

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