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

Adds substantial non-obvious behavior beyond the annotations (which already declare non-destructive, closed-world): figures must reference claims-registry entries, ungrounded figures are returned in a listed result, and such a version cannot be approved. This is real operational context. It stops short of stating who may approve, what errors surface on a rejected version, or what the returned listing looks like.

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?

Three sentences, front-loaded with the action, then the grounding constraint, then the approval gate. No restatement of the title and no filler.

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?

Covers the hardest constraint (claim grounding) and the propose-vs-approve lifecycle well, and an output schema exists so return values needn't be spelled out. But with 8 parameters, nested section/figure and thesisMatch objects, and only 25% schema description coverage, the description leaves an agent guessing about most of the payload structure.

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 25% across 8 parameters, so the description must compensate. It does explain the grounding contract for the section figures (claimRef/grounded/screened) and clarifies that relationshipId selects the tailored variant, but says nothing about thesisMatch, tailoringNote, sections/position, or proposedByAgent.

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 — 'Propose a draft investor memo' — and immediately disambiguates the two modes: the archetype or a variant tailored for one relationship. An agent can distinguish this from fundraising_approve_memo_version or fundraising_get_memo purely from the description.

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?

The lifecycle boundary is explicit: 'Proposes only: nothing is shared or cited until a member approves it,' which implies the approval step exists elsewhere. However, it never names the specific sibling that performs approval or the conditions under which an agent should prefer proposing an archetype versus a relationship-tailored variant.

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