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

The description goes beyond annotations by detailing the response structure (FLAT format mapping), and clarifies the semantic of 'saved_schema_deployed' field with conditions (true when last deploy applied it, false when saved after last deploy, null when no deployed schema). This adds significant behavioral context about the response state that annotations do not cover. Annotations already indicate read-only, idempotent, non-destructive, so description complements rather than contradicts.

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 efficient and front-loaded with the core purpose in the first sentence. It then adds structured use cases and a clear explanation of the response field. Slightly verbose due to multiple use cases and detailed response semantics, but each section is purposeful and well-organized.

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 simple read-only tool with one parameter, the description covers the output format and the meaning of key fields, which is enough for correct invocation. It is complete for the task—no ambiguity remains about what is returned or how to interpret the result. The presence of an output schema is not required, but the description substitutes it well.

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 input schema already fully describes the single parameter (project_id with description 'Project ID (UUID)'), so schema coverage is 100%, earning the baseline of 3. The description does not add new parameter semantics, but it reinforces the project context. No further compensation needed.

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 clearly states the tool retrieves the JSON schema of a project in FLAT format, distinguishing it from siblings like get_graph_schema or get_schema_at_version by specifying the format and use cases. The verb 'get' with a specific resource ('schema definition of a project') makes the purpose unambiguous.

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 provides explicit use cases ('Review current schema before making updates', 'copy schema as template', etc.) and implicitly contrasts with version-specific tools. It names the format required for related tools (create_project, update_schema), aiding selection. It does not explicitly exclude alternatives, but the use cases are specific enough.

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