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

Annotations already declare readOnly, non-destructive, closed-world, so safety is covered; the description adds genuinely new behavioral context by stating the exact authorization scope required (request.read vs audit.read). It also enumerates the kinds of records returned, giving an implicit sense of output shape without an output schema.

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?

Two sentences, no filler: contents first, then the permission caveat. The 'story' framing is slightly colorful but does not obscure the purpose, and nothing in the text is redundant with the schema or annotations.

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?

With no output schema, the description carries the burden of describing return content, and it does so by listing the constituent records (conclusion, human block, AI judge assessments, escalation steps, claims) plus the auth requirement. Minor gaps remain around ordering, time window, and whether pagination applies.

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 100% and the schema itself explains request_id with an example (audit event subject_id when subject_type is approval_request), so the description adds nothing about the parameter. Baseline 3 applies when the schema does all the work for a single required parameter.

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?

Names a specific verb and resource ('Tell one approval request's story from its audit events') and enumerates what the timeline aggregates: pipeline conclusion, human block, AI judge assessments, escalation steps, claim history. This implicitly separates it from raw audit-event tools like get_audit_event/list_audit_events, though it never names them explicitly.

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 permission note ('Needs only request.read on the request, not audit.read') effectively routes an agent here instead of to audit-event tools when it lacks audit.read, and the 'one approval request' framing limits scope. It stops short of an explicit when-not or a named alternative tool.

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