add_project

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

No annotations are provided, so the description carries the full burden and does meaningfully discharge it: it discloses side effects (creates a Qdrant collection, kicks off a background initial index) and two failure conditions. It stops short of describing idempotency, permissions, or what happens if indexing fails partway.

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?

Three tight sentences with the core action front-loaded, followed by side effects and then error conditions. No filler or restatement of the tool name.

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?

An output schema exists, so return values need no explanation, and the description covers the mutation's side effects and error cases. For a no-annotation write tool it is nearly complete, missing only permissions/auth requirements.

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 single parameter has 0% schema description coverage, so the description must compensate. It adds real meaning by specifying the path must be an absolute project directory and must already exist, though it gives no format examples or edge-case handling.

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?

Specific verb ('Register') plus resource ('absolute project directory') plus domain ('semantic indexing'). It clearly distinguishes itself from siblings like remove_project, list_projects, and reindex_project.

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?

Names a sibling for follow-up ('check progress with index_status') and states two preconditions that cause errors (path missing, already registered). It does not explicitly contrast with reindex_project, which the 'already registered' clause implies but never names.

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