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

Annotations already declare destructiveHint=true, openWorldHint=true and readOnlyHint=false, and the description usefully adds the authorization prerequisites (current agency roles, client memberships, owner approvals) and per-family write scopes. It does not say what 'offboard', 'revoke_approval' or 'apply_update' actually destroy or whether they are reversible, so the destructive surface stays opaque. The instruction to reuse the idempotency key sits oddly against idempotentHint=false, though the explicit key parameter mitigates rather than contradicts it.

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?

Length is moderate, but the opening sentence is vague scene-setting and 'Configuration, test proof, activation, collection and outcomes stay distinct' is opaque jargon that costs a sentence without telling an agent anything actionable. The genuinely useful content (auth requirements, scopes, preview-before-approve) is buried mid-paragraph.

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?

An output schema exists, so return values needn't be explained, but for a destructive, multi-action, permission-gated tool the description omits the per-action semantics and the meaning of the required concurrency/fingerprint parameters. An agent still cannot tell what each command variant does or what guarantees apply after calling it.

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% against an eleven-variant oneOf with fields like expectedRevision, fingerprint, subjectHash, choices, updateId, sessionId and rollbackRevision. The description mentions the command schema and idempotency key but explains none of these fields, their formats, or the preview-then-approve sequencing between fingerprint and expectedRevision, so it does not compensate for the coverage gap.

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 verb is generic ('Manage') but the resource (installations) and lifecycle stages (configuration, activation, collection, outcomes) are indicated, so the domain is inferable. However the description never enumerates or characterizes the action set (preview/approve/pause/offboard/apply_update) that the schema actually exposes, and it doesn't clearly separate this tool from siblings like agency_enrollments or agency_offers beyond a passing mention of scopes.

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?

It does prescribe a workflow: inspect the command schema, review exact previews before approval, reuse the same idempotency key, and it states which scope gates which action family. What is missing is any explicit 'use this instead of X' routing versus the many agency_* siblings, and no statement of when a given action (preview vs approve vs offboard) applies.

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