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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the mutation profile is carried by structured data. The description adds the consent constraint ('only when the owner says so'), which is context not present in annotations, but it never says what state change or record is actually written, what existing data is overwritten, or whether the transition can be undone.

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, no redundancy, with the action stated first and the constraint second. Sizing is appropriate for a narrow single-parameter status tool, though the second sentence is terse to the point of being cryptic.

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?

This is a destructive, open-world mutation with no output schema and no documented parameters; the description covers only the action and a consent gate. It leaves unresolved what actually gets recorded or transitioned, what happens to the prior pitch state, and what the caller should pass, which is too much for an agent to safely execute a destructive write.

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% for the single pitchId parameter, so the description must compensate and it does not mention pitchId at all. The schema supplies type and UUID format, but the agent gets no guidance on which pitch identifier to use or where to obtain it.

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: 'Record that the creator replied', which maps directly to a pitch lifecycle status marker. An agent can distinguish it from read tools like soclo_creators_pitches, but the description never differentiates it from neighbours in the same pipeline such as pitch_sent, pitch_approve, or pitch_reject.

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?

'Only when the owner says so' is a real gating condition that tells the agent this must not be inferred autonomously, which is valuable. However, no alternative tool is named and no preconditions are given (e.g., does the pitch need to be in 'sent' state first?), so the agent must infer when this applies versus the other pitch_* status tools.

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