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

Annotations already declare readOnly=false, destructive=true, idempotent=true, openWorld=true; the description adds real value beyond them by clarifying that approval does not trigger delivery. It does not address reversibility (can a pitch be un-approved?), what the destructive status change affects, or permission requirements for the owner.

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 short sentences, zero filler, with the core action front-loaded and the critical non-send caveat immediately after.

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 single-parameter mutation with no output schema, the description covers the most important gotcha (no send occurs). It leaves gaps around what the resulting state is and whether approval can be undone, which matter given destructiveHint=true.

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 0%, but there is only one parameter and the schema itself encodes uuid type plus a strict pattern. The description says nothing about pitchId, relying on the tool name ("pitch") and structured format to make it inferable.

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 ("Mark a pitch as approved") and adds the actor (owner), so the action is unambiguous. It implicitly contrasts with sending/rejecting siblings via the second sentence, but never names an alternative tool, so sibling differentiation is only partial.

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?

"This does not send it" gives one useful usage boundary — approval is a distinct step from dispatching — which implies the agent should use a send/pitch_sent tool afterwards. However, no conditions, prerequisites, or explicit alternatives (reject, sent, replied) are stated.

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