grant_scope

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

No annotations exist, so the description carries the full burden. It does disclose a real behavioral constraint (the org's owner plan must be Kiln Business, but grantees on any plan can read it), which is useful. It omits mutation semantics entirely: whether re-granting duplicates, whether grants are revocable, how expires_at behaves, and what authorisation the caller needs.

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?

Only the first sentence earns its place; the remaining three sentences are marketing copy and an upgrade URL that consume roughly two-thirds of the text without informing invocation. The one substantive constraint is front-loaded, but the bulk is waste.

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?

Against a 7-parameter mutation tool with no annotations, no output schema, and 0% schema coverage, the description leaves too much unsaid: expiry semantics, granted_by identity, org scoping, duplicate-grant behaviour, and revoke path are all absent. The plan-gating note is the only genuinely compensating content.

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 description coverage is 0% across 7 parameters, so the description must compensate and does not. It explains capability and scope_key only in tautological terms and gives a useful tenant/team either-or hint, but org_id, granted_by, and especially expires_at (numeric, unit unclear) are entirely undocumented, as is any required-one-of constraint between tenant_id and team_id.

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 (Grant) and resource (capability on scope_key), and the phrase 'to a tenant OR a team' clarifies a mutually-exclusive targeting choice the schema does not express. It stops short of 5 because the sibling revoke_scope is never named, so an agent must infer the inverse tool from the name alone.

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 'tenant OR team' phrasing implies which target to pick, but there is no statement of when to grant versus when to revoke, no prerequisites about caller permissions, and no mention of the license-gated failure mode beyond a vague plan note.

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