list_scopes

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

With no annotations, the description carries the full burden, and it does disclose one real behavioral trait: the org (its owner's plan) must be on Kiln Business while the caller's own plan is irrelevant — a precondition that explains a likely failure mode. It says nothing about pagination, ordering, or result shape, and roughly half the text is upgrade promotion rather than tool behavior.

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 one useful sentence is correctly front-loaded, but it is followed by three sentences of marketing copy and a pricing URL that consume most of the definition without helping the agent invoke the tool. The plan-gating fact is buried inside upgrade messaging rather than stated as a condition.

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 three-parameter list tool with no annotations and no output schema, the description should clarify what a returned 'grant' contains and how the scope is gated. It gestures at the plan gate but omits return shape, pagination, and the effect of omitting both tenant_id and team_id, leaving real gaps filled by advertising.

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 0% with three parameters, so the description must compensate. It clarifies that tenant_id and team_id are alternative filters ('OR'), a constraint the schema does not express, but leaves org_id's relationship to team_id/tenant_id, identifier formats, and behavior when no filter is supplied unspecified.

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 opening sentence gives a specific verb and resource — 'List grants for an org' — and adds scope ('optionally filtered by tenant OR team'), which distinguishes it from the mutation siblings grant_scope and revoke_scope. It does not explicitly name an alternative tool, but the purpose is unambiguous.

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?

'Optionally filtered by tenant OR team' implies the filter is optional and that tenant and team are mutually exclusive, which is genuine usage guidance. However, nothing states when to prefer it over list_org_members / list_team_members / list_role_templates, and no prerequisite conditions for calling are laid out as instructions.

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