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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond them: this saves a full revision rather than a diff, and activation is the default unless activate is false. It also describes the policy's runtime effect (how members get paged), which is beyond annotation scope.

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?

Front-loaded with the core action and kept to three sentences with no filler. The middle sentence on paging behavior is dense but earns its place by explaining the domain semantics of the document being saved.

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 complex nested-object tool with no output schema, the description covers the key agent needs: overwrite semantics, activation default, the nodes grammar pointer via read_reference, and the prerequisite. Minor gaps remain (no success/error behavior or validation notes), but annotations carry the safety profile and read_reference carries the grammar.

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 100%, so baseline is 3, but the description adds meaning on top: it clarifies that nodes is the whole document (not a diff), that levels name current members as user targets or one broadcast target, and that activate defaults to true. This reinforces and disambiguates the schema rather than repeating it.

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?

Specific verb+resource ('Save a new revision of a team's escalation policy') with scope made explicit ('the whole document again, not a diff'). The phrase 'and activate it unless activate is false' also disambiguates it from the sibling activate_team_escalation_policy_revision, so an agent can tell them apart.

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?

Provides an explicit prerequisite — 'Call read_reference (escalation_paths) first' — which is real routing guidance. It does not state when to prefer this over alternatives (e.g. activate_team_escalation_policy_revision or create vs update), so it stops short of full when/when-not coverage.

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