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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered structurally. The description adds genuinely useful context the annotations cannot express: company-admin authority is required, the effect lands on exact revisions, an audit history entry is created, and shared clinical/identity/approval boundaries persist. It stops short of explaining optimistic-concurrency failure behavior or why an idempotency_key exists despite idempotentHint=false.

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 core action is front-loaded, which is good, but the middle sentences are telegraphic fragments ('Shared clinical/identity/approval boundaries remain') that read as internal shorthand rather than agent-usable guidance. Roughly the right length, but several clauses spend words without resolving meaning.

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 destructive, admin-scoped, open-world mutation with a nested schema and no output schema, the description covers purpose, scope boundaries and the forLaunch branch. It does not cover what a caller should do about revision conflicts, what success returns (no output schema exists), or the full meaning of the required revision set — meaningful gaps for this risk level.

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 only 17% (just idempotency_key), and there are six parameters including a nested documentRevisions object. The description explains forLaunch ('checks the selected company AI employee and four company facts; other policies are optional') but says nothing about expectedRevision semantics, the three required document revision keys, or why reason is mandated — leaving the two most safety-critical inputs undocumented in both places.

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 concrete verb+resource: applying a reviewed saved policy draft to exact company knowledge revisions, with the authority model and audit consequence named. It is distinguishable from summer_onboarding_policies_read/save and summer_knowledge_shared_publish, though the phrasing 'exact company knowledge revisions' is dense jargon that assumes domain familiarity.

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?

Explicit exclusions ('does not publish public articles, activate integrations, change hours/billing or approve customer effects') plus 'existing operations libraries use their normal knowledge editor' give clear when-not routing. What is missing is the positive precondition chain — that a draft must first exist via summer_onboarding_policies_save — and an explicitly named alternative tool.

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