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

Annotations already declare readOnly=false, idempotent=false, destructive=false. The description adds genuine behavioral detail beyond that: partial-update semantics where unspecified fields are preserved, which tells the agent this is a merge-style PATCH. It stops short of covering permissions, error behavior, or what happens when a nested 'data' object is replaced vs merged.

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 short sentences, front-loaded with the action and followed immediately by the key behavioral caveat. No filler, though it is arguably too sparse rather than inefficient.

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 mutation tool with a nested, open-ended 'data' object (additionalProperties: true, doc link for extra settings) and no output schema, the description covers the merge semantics but leaves gaps: what the response looks like, whether nested objects like 'evaluations' are replaced wholesale, and any permission constraints. Adequate but minimal.

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 both parameters and their nested fields are documented in the schema. The description's 'selected fields / omitted fields retain values' adds a nuance the schema doesn't state (that data is merged rather than replaced), but it gives no per-field meaning beyond that. Baseline 3 is appropriate with the small added omission semantics.

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 and resource ('Update selected simulation scenario fields'), making it clearly distinct from create/get/delete siblings. It doesn't explicitly name what it is not, but the resource granularity (scenario vs simulation vs persona) is unambiguous from the name and description together.

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 phrase 'omitted fields retain their values' implies partial-update usage, which is mildly useful guidance. However, there is no explicit statement of when to use this vs update_simulation or create_simulation_scenario, and no prerequisite or eligibility notes.

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