get_project_status

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

No annotations provided, so description carries full burden. It states the tool reads registry and enriches from folder card if folder exists. Implies read-only by 'Reads' and 'shows', but does not explicitly state it is non-destructive or list permissions. Slight gap, but otherwise transparent.

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?

Description is a paragraph with some repetition (e.g., mentions empty project_id behavior twice). Could be more concise by combining sentences, but still efficient and front-loaded with purpose.

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 output schema exists (so returns are documented) and only one parameter, the description covers all needed behavior: what it returns, how parameters behave, and enrichment logic. No missing crucial information.

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?

Single parameter `project_id` has 0% schema description, but the description adds full semantics: empty string returns all active projects, specific (exact or partial) returns that one enriched from folder card. This is highly informative beyond the basic schema.

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 reads the project registry (the `projects` table) and adds task completion counts. It distinguishes itself from sibling tools like `get_project_categories` by specifying it returns status with counts, not just categories. The verb 'Reads' and resource 'project REGISTRY' are specific.

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?

Explicitly explains when to use: for registry status (not folders on disk), and behavior based on project_id: empty lists all active projects, specific shows enriched data. This guides the agent against alternatives like `scan_project_folder`.

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