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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is known. The description adds nothing beyond that — it does not say whether the draft is deleted permanently, whether the creator is notified, whether the pitch can be restored, or what state results. For a destructive operation this leaves real questions unanswered.

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?

It is short and front-loaded, but the brevity is under-specification rather than efficiency: the single five-word phrase contains no actionable detail, so the sentences that should earn their place are simply missing.

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 destructive, open-world mutation with an undocumented parameter and no output schema, the description should at minimum characterize what is destroyed and what a caller gets back. None of that is present, so an agent cannot confidently invoke it beyond string-matching the tool name.

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?

There is a single required pitchId parameter with 0% schema description coverage, and the description does not explain it at all — no indication of whether it refers to a draft ID, a creator ID, or a pitch thread. The schema pattern at least reveals UUID format, but nothing in the description compensates for the coverage gap.

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?

"Discard a pitch draft" gives a verb (discard) and a resource (pitch draft), so the basic operation is inferable. However, it never distinguishes itself from close siblings such as soclo_creators_pitch_approve, soclo_creators_pitch_edit, soclo_creators_pitch_sent, or soclo_creators_dismiss, and the name/verb mismatch (reject vs. discard) leaves the precise semantic fuzzy.

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?

There is no guidance on when to use this tool, no preconditions, and no mention of alternatives. An agent must guess whether discarding is appropriate versus editing, sending, or simply dismissing the pitch.

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