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

Goes well beyond the annotations by disclosing the insert-or-replace semantics, the ≤10000 weightBps invariant, the critical gateway-vs-on-chain enforcement difference (partial mixes accepted here, exact 10000 enforced on-chain), and the return shape. Annotations only say it is a non-read-only, non-destructive write, so this text carries real operational weight.

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 dense sentences, front-loaded with the action and the invariant, then the return value. Slightly jargon-heavy ('LicensingEngine', 'CompositionManifest') but every clause earns its place; nothing is wasted.

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 4-param write tool with no output schema, it covers mutation semantics, the key domain invariant, enforcement divergence, and the return fields {modelIpId, manifestHash}. The one gap is failure behavior when the gateway rejects or when the sum is invalid.

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 the schema already documents all four parameters, their optionality, and the weightBps range. The description reinforces the summation constraint in prose but adds no new parameter-level detail (e.g., what happens if the sum exceeds 10000). Baseline 3 is appropriate.

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?

States a specific verb+resource ('Set (insert-or-replace) the TrainingManifest for a model IP') and explains the domain role: it is the dataset weight map the LicensingEngine walks when distributing payouts. The paired sibling pcc_training_manifest_get makes the get/set distinction explicit.

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 when you'd need it (to define payout distribution for a model-author entry), but gives no explicit when-to-use framing or exclusions. It never names pcc_training_manifest_get or warns about overwriting an existing manifest, which is the main alternative/risk an agent must weigh.

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