Pull Excalidraw canvas

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

With no annotations, the description must carry the behavioral disclosure burden. It indicates a read-like behavior ('returns a document') and a precondition, which is useful, but it does not explain what happens when the revision is not stale, whether any server interaction or validation occurs, or what errors may arise. These gaps prevent a higher score.

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 a single, compact sentence with no filler words. However, it is so terse that it sacrifices important clarifying details, such as what 'bound document' means and the exact behavior when 'app revision' is not stale, so it earns a strong but not perfect conciseness score.

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 there is no output schema and no annotations, the description leaves too much unstated: the return value's format, behavior for a non-stale revision, error handling, and how currentRevision influences the call. The low tool complexity makes a more complete description feasible, but this one leaves the agent guessing about key operational details.

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 only 50%: canvasPath is documented in the schema, but currentRevision is described only by a regex pattern. The description adds no parameter-level meaning—it mentions 'app revision' indirectly but never explains the currentRevision parameter, its purpose, or how it interacts with staleness. The description fails to compensate for the schema's missing documentation.

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 names a specific action ('returns') and resource ('the bound document') and adds a distinctive condition ('when the app revision is stale'), which goes beyond a mere restatement of the title. However, 'bound document' is somewhat ambiguous and the description does not explicitly differentiate pull_canvas from sibling read tools like open_canvas or inspect_canvas.

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 clearly states when to invoke the tool: when the app revision is stale. This provides a concrete use condition, but it does not mention when not to use it or name any alternative sibling tools, so the guidance is helpful but incomplete.

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