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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-obvious context: no provider requests are issued and 'an unknown cost is NOT a quote', which prevents an agent from misreading validation output as pricing — a real semantic guard beyond the annotations.

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?

Three short clauses, front-loaded with the read-only nature and the validation scope, with the cost caveat last. No filler; every phrase either scopes the operation or rules out a misinterpretation.

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?

There is no output schema, so the description should hint at the shape of the result (blocker list, pass/fail, warnings). It lists what categories are validated, which partly covers this, but an agent cannot know how failures are reported or whether validation returns structured blockers.

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% on the single project_id parameter, but the parameter is a self-explanatory required identifier and the description adds nothing about it. An agent needs no elaboration to supply a project_id, so baseline 3 is appropriate rather than a penalty.

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 description names a specific verb (validate) and resource (Canvas graph) and enumerates what is checked: dependency order, missing models/media, continuity blockers. It distinguishes itself from the execution path by explicitly excluding prepare_execution/provider requests, though it does not name the sibling tools it substitutes for.

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?

Usage is conveyed only negatively — 'No billing, no prepare_execution, no provider requests' tells the agent when NOT to use or expect this, which implies the execution tools handle those cases. There is no positive statement of when to call it (e.g., before apply/start_execution) or any prerequisites.

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