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

Annotations only declare readOnlyHint=true, but the description adds substantial behavior: login is required, results are trimmed per viewer (real users/cloud users and match edges are all scoped to the caller), the list is capped at ≤60 items, and GROUP records carry a GRAPH vs THEME origin with scores that are explicitly not commercial commitments. This is exactly the kind of context annotations cannot 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?

Extremely compact — semicolon-separated clauses with the gating constraint (login, viewer scoping) front-loaded, and no filler sentences. The long six-tool chained workflow is dense and slightly hurts scanability, but every clause carries information an agent needs.

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 3-parameter read-only tool with no output schema, the description covers access requirements, result scoping, result cap, status defaults and type semantics. Minor gaps remain: no ordering guarantee for the returned proposals and no guidance on what a proposal object contains, though the absence of an output schema limits how much is owed.

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 only 33% (only organizationId is documented), so the description has to compensate, and it largely does: status defaults to SUGGESTED, ALL expands to SUGGESTED+CONVERTED, and DISMISSED must be passed explicitly — precisely the default/enum semantics missing from the schema. It also disambiguates kind (PAIR vs GROUP). Enum value meanings are covered; nothing else is needed.

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?

Opens with a specific verb and resource: list proposals the viewer has rights to in an organization/alliance, split into PAIR (two-person matchmaking) and GROUP (AI-arranged meetups). The PAIR/GROUP distinction separates it from generic listing siblings, though it never explicitly contrasts with close neighbors like list_organization_match_pairs or list_my_organization_matches.

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?

Provides an explicit workflow anchor: list_my_spaces(matchAdmin) → this tool → get_organization_proposal_activity_draft → create_organization_proposal_activity → ... → invite_organization_meetup_to_activity, plus a PAIR-only branch to introduce_organization_proposal. That tells the agent both prerequisites and follow-ups. It stops short of stating when not to use this tool (e.g., versus listing match pairs directly).

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