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

The description goes beyond the annotations (readOnlyHint=false, destructiveHint=false) by disclosing that the call creates an independent DRAFT, that it replaces nothing in the pool, that the draft persists until approved/revised/discarded, and that it must be shown back to the user verbatim. This is meaningful safety-relevant behavior that the annotations alone could not convey.

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?

The description is long, but nearly every clause earns its place: writing constraints, an example, privacy rules, and the approval/revision protocol. It loses one point because a couple of rules are duplicated between description and schema (character limit '200–1500 characters'), and the example, while helpful, extends the length noticeably.

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 tool with no output schema, the description fully specifies what the agent must do before calling it (draft from conversation), what it must do after (show verbatim and ask approval), and how to handle each user response (approve→confirm, change→recreate, decline→withdraw). The expected return behavior is fully covered, leaving nothing for the agent to guess.

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?

Although schema coverage is 100%, the description adds substantial meaning: it specifies the sentence count, person, character bounds, third-party wording ('words of the user, not formal or clinical'), the three content areas (situation, where the user is in it, wanted help), and the anti-hallucination/PII rules. It also clarifies the replaces_draft_id semantics within the revision workflow, which the schema states only tersely.

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 opens with a precise verb+resource: 'Submit what the user is going through, to find someone living through something similar.' It clearly defines the deliverable (a match request) and its social function, and its content rules (third person, 2–5 sentences, 200–1500 characters) make it unmistakable against siblings like confirm_match_request or withdraw_match_request.

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?

Explicit when/when-not guidance is present: call confirm_match_request only after the user approves the exact version, call create_match_request again for revisions (with replaces_draft_id), and call withdraw_match_request if the user declines. No inference is required to route between the two siblings that act on the draft.

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