memvid_vec_search

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

Annotations indicate readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false, covering safety and idempotency. The description adds value by specifying 'vector-only similarity search', which clarifies the search method (semantic vs. other types) and implies it's for similarity-based retrieval, not exact matches. It doesn't contradict annotations, and it provides useful context beyond them, though more details on output or limitations could enhance it.

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 extremely concise with 'Vector-only similarity search (semantic search)', a single phrase that front-loads key information. Every word earns its place by specifying the method and type of search, with no wasted text. It's appropriately sized for a tool with clear annotations and schema.

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 the tool has annotations covering safety (readOnly, non-destructive, idempotent) and a well-documented input schema, the description is adequate but minimal. It lacks details on output (no output schema provided) and doesn't fully address when to use it versus siblings. For a search tool with 3 parameters and no output schema, more context on result format or limitations would improve completeness, but it's not incomplete enough to score lower.

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%, with clear descriptions for 'file' (path to .mv2 memory file), 'query' (search query text), and 'limit' (maximum results). The description doesn't add meaning beyond the schema, as it doesn't explain parameter interactions or usage nuances. With high schema coverage, the baseline score of 3 is appropriate, as the schema already documents parameters effectively.

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 'Vector-only similarity search (semantic search)' states the action (search) and method (vector/semantic), but it's vague about the resource being searched (memory files). It doesn't distinguish from siblings like 'memvid_find' or 'memvid_search' (if they existed), though 'memvid_find' might be a different type of search. The purpose is understandable but lacks specificity about what's being searched.

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?

No guidance on when to use this tool versus alternatives is provided. The description mentions 'vector-only' and 'semantic search', but it doesn't explain when this is preferable over other tools (e.g., 'memvid_find' might be keyword-based). There's no mention of prerequisites or exclusions, leaving usage context implied at best.

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