get_annotations

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does this exceptionally well: it documents what every returned field means, notes that elementHints are statically extracted from source and may be inaccurate, and defines brokenRefs. This is far more transparent than a typical one-line description and gives the agent accurate expectations.

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 dense sentence with semicolon-separated fields, and every segment adds distinct information. The critical warning about elementHints is embedded without bloat. It is longer than ideal, but the structure is clear and there is no waste, so it earns a high 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?

There is no output schema, so the description must explain return values — and it does so comprehensively. It covers all seven return fields, their meanings, provenance, and reliability caveats. For a read tool with this complexity, nothing essential is missing, and the agent can correctly interpret the result.

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?

The schema already describes dir and projectId, covering 67% of parameters. The description adds little direct parameter meaning beyond referring to '这块画板' (this artboard), which implicitly maps to artboardId. Since the description does not compensate for the undocumented artboardId, the score stays at the baseline for moderate schema coverage.

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 opens with '返回这块画板的标注' (Returns annotations for this artboard), a specific verb and resource, then enumerates the exact return fields (md, refs, elementIds, elementHints, sourceHash, validatedHash, brokenRefs). This makes the tool's purpose unmistakable and naturally distinguishes it from write_annotations and other sibling tools.

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 offers practical usage notes, such as warning that elementHints are only guesses and should not be directly used as display names, and it explains dir resolution behavior. However, it never explicitly states when to choose this tool over alternatives like write_annotations or get_guide; the context is implied rather than clearly routed.

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