scf_update_evidence

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

Annotations only indicate non-read-only and non-destructive, but the description adds meaningful behavioral details: it is a write operation requiring editor+ role, it creates the tracking row if missing, and it applies only provided fields. This is valuable context beyond the structured annotations and there is no contradiction.

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 two sentences with no filler. The core operation and scope are front-loaded, and the partial-update behavior is stated concisely.

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 10 parameters and lack of an output schema, the description covers the essential operational semantics: upsert behavior, permissions, and partial updates. The schema handles parameter-level details. A minor gap is the lack of any statement about the response shape, but this is not critical for invoking the tool.

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?

All 10 parameters already have schema descriptions, so the schema carries most of the burden. The description adds important semantic context by clarifying that all body fields are optional and only provided fields are applied, which materially changes how an agent should construct a request.

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 identifies the action as an 'upsert' of 'tracking fields' on an evidence item, distinguishing it from simply creating or reading evidence. It also names the required role ('editor+'), which helps an agent understand the operation's nature. It is specific enough to separate this from siblings like scf_create_evidence and scf_list_evidence.

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 states clear context: use this to upsert tracking fields and create a missing tracking row. It does not explicitly name or contrast alternatives such as scf_create_evidence, so the when-not-to-use guidance is only implied rather than explicit.

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