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

Annotations already declare readOnly, idempotent, openWorld, non-destructive, so the safety profile is covered. The description nonetheless adds genuinely useful operational context the annotations cannot: 24h KV cache, 5-minute per-origin cooldown on fresh, 30/min rate limit, and that verify withholds credit for dead endpoints. Return shape is also enumerated (grade, score, subscores, conformance_summary, connect_recipe, permissions, manifests), which is valuable given no output schema exists.

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 primary action and appropriately sized for a 10-parameter tool; nearly every clause carries information. It is, however, a single run-on sentence with stacked parentheticals, which makes it denser to parse than it needs to be.

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?

Covers both invocation modes, the key modifiers, caching/cooldown/rate-limit constraints, and the return payload — enough to call it correctly with no output schema available. The only soft spot is that the interaction between diff and a prior snapshot baseline is stated but not fully defined (where the baseline originates).

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%, so every parameter is already documented; baseline is 3. The description does add mode-combination guidance (verify, bridge, diff, brief/compact) and the rate/cooldown consequences of fresh that the schema only hints at, but it does not add syntax or format detail beyond the schema text.

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+resource (audit an origin's manifests, grade it) and covers the second mode (in-memory local validation) in the same breath. It explicitly contrasts with siblings probe and template, so an agent can choose without opening any schema.

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 final sentence states the routing rule directly: conformance grading and local linting here, ungraded discovery via probe, starter scaffolding via template. The two invocation modes are also gated by concrete conditions (pass origin to fetch; pass id + content to avoid network).

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