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

The annotations already establish read-only, idempotent, and non-destructive behavior. The description adds useful context by stating results are 'precomputed SigLIP neighbours', implying results may be static and not include very recent projects, and specifying the similarity dimensions.

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 fits in one sentence, front-loads the core purpose, and efficiently includes the algorithm and input source without any redundant text.

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 retrieval tool with good annotations and full schema coverage, the description adequately covers what it does, how to get the slug, and the nature of the results. It doesn't describe return format, but the absence of an output schema and the simplicity of the tool make this acceptable.

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 fully describes both parameters (slug and limit), so the baseline is 3. The description adds value by telling the agent to take the slug from search_projects results, which is a crucial semantic hint beyond the 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 identifies the resource ('projects') and the method ('visual + semantic similarity'), and differentiates the tool from siblings by referring to the slug from search_projects. However, it lacks an explicit verb like 'retrieve' or 'list', relying on the title and context to imply the action.

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?

It explicitly tells the agent to use slugs from search_projects results, which gives clear context for when this tool is appropriate. There is no explicit comparison to alternatives or 'when not to use', but the input requirement narrows the use case sufficiently.

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