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

Annotations already declare read-only, idempotent, non-destructive semantics, so the bar is low. The description adds a real prerequisite ('requires the org's RAG index to be populated (Azure OpenAI required)') and the return shape ('up to 5 matches with similarity scores'), which are genuine operational facts the annotations do not carry.

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 compact sentences, front-loaded with the verb and resource, then parameter choice, then returns and prerequisite. No filler; every sentence carries information an agent needs.

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 vector-search tool with no output schema, the description covers purpose, input selection, expected returns (count + scores) and the environmental prerequisite. It is essentially complete, with only minor omission of behavior when the RAG index is empty.

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?

Schema coverage is 100%, so the baseline is 3. The description goes slightly beyond by characterizing projectId as 'similar to this project' and description as 'free-form', giving the semantic intent behind each mutually exclusive choice rather than just repeating the exclusivity constraint.

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+resource ('Find projects in this org similar to...') with two clearly named input modes. An agent can distinguish it from generic sibling searches like search, search_docs, or search_org_knowledge because the target is project similarity, not document/knowledge lookup.

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?

States the trigger condition explicitly ('have we done a project like this before?') and clarifies the two mutually exclusive entry modes (projectId vs description). It doesn't name an alternative sibling to route to when the RAG index is unavailable, so it stays short of a 5.

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