project_update

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

Annotations are all false (readOnlyHint=false, destructiveHint=false), so the description carries the behavioral burden. It adds three genuinely useful traits: atomicity of the update, the optimistic-concurrency requirement (expected_revision), and a specific failure mode (UPM changes on nonempty fonts fail). This goes well beyond the bare annotations without contradicting them.

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 tight sentences: the first front-loads purpose and atomicity, the second adds the revision requirement and a failure caveat. No filler, though 'nonempty fonts' is slightly cryptic without definition.

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?

An output schema covers return values, and the description addresses the key gotchas (revision, UPM failure). But it leaves gaps: how to obtain expected_revision, what happens on mismatch, and whether multiple sub-resources can be updated in one call (atomicity hints yes but is unstated). Adequate but not comprehensive for a 7-parameter mutator.

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?

With 0% schema description coverage, the description must compensate for the 7 parameters. It covers expected_revision, metadata, brief, decision, and UPM (units_per_em) conceptually, but it omits summary, project_id, and any detail about the nested Metrics/Decision/Metadata structures. Partial compensation, not full.

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 uses a specific verb ('update') with a clear resource ('metadata, brief or decision journal'), which distinguishes it from siblings like project_create and project_inspect. It doesn't explicitly name a differentiating sibling, but the scoping to project-level sub-resources makes the purpose unambiguous and non-tautological.

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 description implies usage context through 'Requires expected_revision,' which signals a concurrency-control workflow (obtain revision, then update), and the UPM caveat warns against a failure condition. However, it never explicitly states when to prefer this over project_create/project_inspect or what to do when the revision mismatches — the workflow is implied rather than stated.

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