project_summary

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

No annotations exist, so the description introduces some behavioral detail: it explains the design consistency score is 'based on color/font overlap across screens,' implying the analysis also crosses screens. But it does not mention side effects, error behavior, or the fact that it may fetch remote HTML (though that is in the schema). The transparency is adequate but not heavy.

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, tightly packed sentence with the main outcome front-loaded ('Returns a high-level summary') followed by a comma-separated enumeration of what that summary covers. There is no filler, repetition, or tangential detail.

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?

For a tool that only fetches summary data and has no output schema, the description is quite complete: it lists what the agent can expect to receive. It does not specify error cases or ordering of the screen list, but those are not critical for correct invocation. The missing output-schema risk is largely mitigated by the explicit return-field enumeration.

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 covers 100% of parameters with descriptions, so the baseline is 3. The prose goes beyond the schema by linking analyzeConsistency and maxScreensToAnalyze to the definition of design consistency (color/font overlap), effectively explaining why those parameters matter. It adds context that helps an agent set them appropriately, earning one point above the baseline.

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?

Description opens with a concrete verb ('Returns') and a specific resource ('a high-level summary of a Stitch project'), then enumerates the summary's contents (screen count, screen names, common patterns, design consistency score, device type distribution). This clearly distinguishes the tool from siblings like get_project, which likely returns detailed project info, or list_screens, which lists screens only.

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 makes it clear the tool is for high-level summaries, so an agent can infer when to use it. However, it does not explicitly state when to choose it over comparable tools (e.g., get_project, list_screens) nor mention any exclusions, prereqissism, or alternative-recommended conditions.

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