write_update

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

The description adds substantial behavioral context beyond the annotations: values are 'validated against the catalog before sending', the response is read back and non-persisted values are reported, and writing Effort bypasses role efforts. These disclose real side-effect and verification behaviors. The destructiveHint=true and readOnlyHint=false annotations are consistent with the described write behavior. The unexplained 'layer 1' phrase slightly detracts, since it obscures rather than clarifies scope.

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?

Three sentences, each earning its place: the primary action with validation, the read-back verification behavior, and the alternative routing. The main action is front-loaded ahead of caveats, with zero redundancy or filler.

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?

The description covers key runtime behavior — validation, persistence verification, and the Effort trap — which partially compensates for the missing output schema. But it leaves 'layer 1' undefined, does not clarify the boundary with write_update_card, and says nothing about error handling or authorization. For a destructiveHint=true tool with no output schema, a bit more context would be expected.

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 67%, with resource and fields already documented in the schema (including a Targetprocess JSON example for fields). The description adds some semantic nuance — the Effort-bypass warning applies to the fields parameter — but it does not materially explain id or resource beyond what the schema provides. The schema carries the primary burden, so the 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?

The description states a specific action ('Update fields of an existing entity') with a resource and scope. It distinguishes itself from one sibling explicitly ('use write_set_role_effort instead'). However, the qualifier '(layer 1)' is opaque — an agent has no way to know what layer 1 means or whether layer 1 is the right layer — and the description does not differentiate from closely named siblings like write_update_card or write_set_custom_fields.

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 Effort caveat provides an explicit when-not-to-use rule with a named alternative ('Writing a card Effort here bypasses role efforts; use write_set_role_effort instead'). The general use case (updating fields on an existing entity) is clear. It does not, however, discuss when to prefer write_update_card, write_set_custom_fields, or write_create, which are plausible competitors in the sibling list.

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