drawing_update

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

Annotations already declare this is a write (readOnlyHint=false, openWorldHint=true, non-idempotent), so the description's real contribution is the optimistic-concurrency protocol and the promise that each requested property or point is verified after writing. That is meaningful behavior beyond the annotations. It stops short of saying what happens on verification failure (rollback versus partial write), which is the main remaining gap.

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?

A single tight sentence with the conditional guard front-loaded before the verification promise — no wasted words. The density costs a little clarity, since 'independently verify every requested property or point' leaves the verification target implicit.

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?

This is a high-complexity mutation tool: 9 parameters including a nested points array, no output schema, and several empty parameter descriptions. One sentence covering the concurrency guard is not enough — the failure modes, the partial-write behavior, and the semantics of the undocumented boolean flags all go unaddressed.

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 only 44% across 9 parameters, so the description must compensate and largely does not. It references properties, points, and the fingerprint concept but says nothing about id, target_id, expected_layout_id, or the merge-versus-replace semantics of the three boolean flags whose schema descriptions are empty strings.

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 (update) and resource (drawing) and adds two distinguishing clauses: a fingerprint precondition and post-write verification. That scope is clearly different from drawing_get, drawing_create, and drawing_remove in the sibling list, so an agent can tell them apart without opening a schema.

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 precondition 'only if its fingerprint still matches' implies the required workflow — call drawing_get first and pass its fingerprint — but the tool never names that sibling or spells out what to do on mismatch. There is no when-not guidance and no comparison against alternatives such as drawing_create or layout_save.

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