tigergraph__search_top_k_similarity

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description doesn't need to restate safety. It adds valuable behavioral context beyond annotations: the critical warning that 'a dimension mismatch will cause the search to fail or return incorrect results,' and the return format of 'top-K most similar vertices with distance scores.' This is substantive, non-redundant disclosure.

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 efficiently organized: main purpose first, then a bolded IMPORTANT warning, a concrete action step, and a compact related-tools list. Every sentence earns its place, and the critical constraint is front-loaded so it is unlikely to be missed.

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?

With no output schema, the description steps up by stating the return format (top-K vertices with distance scores). It also discloses the primary failure mode (dimension mismatch), directs the agent to a preflight check, and references index-readiness and vector-retrieval tools. For a read-only search tool whose safety profile is fully covered by annotations, nothing essential is missing.

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 description coverage is 100%, so each parameter already has meaningful documentation. The description adds value by elaborating on query_vector semantics: the dimension must exactly match the vector attribute's dimension, with a concrete example (DIMENSION=1536). This goes beyond the schema's generic 'Query vector for similarity search' and compensates for the most error-prone parameter.

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 opens with a specific verb and resource: 'Perform vector similarity search using TigerGraph's vectorSearch() function,' and clearly states the output: 'Returns top-K most similar vertices with distance scores.' This distinguishes it from sibling vector tools like fetch_vector (retrieve specific vectors) and list_vector_attributes (check dimensions), leaving no ambiguity about the tool's role.

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 pre-search guidance: 'Use list_vector_attributes to check the expected dimension before searching.' It also lists related tools with their purposes, giving context for when to use alternatives (e.g., get_vector_index_status to check index readiness). It lacks an explicit 'when not to use this' statement, but the guidance is clear enough for an agent to act correctly.

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