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

The description adds valuable behavioral context beyond the annotations: it details that omitted fields are preserved, how clearSourceRef behaves, and that the updated project is returned. It also notes the incompatibility constraint. Given annotations only provide readOnlyHint=false and idempotentHint=true, the description carries a significant share of transparency, and nothing contradicts 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?

The description is front-loaded with 'Partial update' and then lists fields compactly in one sentence. While long, it is necessary given the 19 parameters and dense information (values, constraints, return). It could be slightly improved with bullet points, but every part earns its place, so it remains well-structured.

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?

Given the tool's complexity (19 parameters, nested sourceRef, no output schema), the description covers all essential aspects: partial update semantics, every updatable field with allowed values, the conflict scenario, and the return value. This makes it complete for an AI agent to select and invoke correctly, and the annotations fill in the safety/idempotency profile.

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?

Since schema description coverage is 100%, the baseline is 3. The description adds meaning by explaining partial update behavior (omitted fields untouched) and consolidating allowed values for multi-choice fields. It reinforces the clearSourceRef/sourceRef conflict already in the schema, but the partial update note is crucial and not conveyed by the schema alone, justifying a 4.

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 clearly states 'Partial update of a project' with a specific verb and resource, and enumerates the updatable fields. This distinguishes it from sibling tools like project-create, project-get, and project-delete. The purpose is unambiguous and informative.

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?

It explicitly explains partial update semantics ('only the fields you pass are changed; omitted fields are untouched'), which guides when to use this tool. It also highlights the incompatibility between clearSourceRef and sourceRef. However, it does not explicitly name alternative tools for full/partial creation or exclusions, though the context makes this clear.

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