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

Beyond the annotations (readOnly, idempotent, openWorld=false, non-destructive), the description discloses non-obvious behavioral traits: the corpus is bundled and versioned with the engine, results are bounded excerpts rather than full documents, coverage is partial so negative results are inconclusive, and there is no repository/internet fallback. These are exactly the caveats an agent needs to interpret misses correctly.

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?

Four front-loaded sentences: what it searches, what it returns and links to, when to use it, and the coverage limitation. Every sentence carries distinct information with no restatement of the name or title.

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 still covers return shape (bounded excerpts plus doc ids), corpus scope and versioning, access limitations, and the false-negative caveat. Nothing an agent needs in order to call this correctly and interpret its results 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% and both parameters are well documented in the schema, including the query examples format and the projectId null semantics. The description adds no parameter-level detail beyond what the schema already provides, so baseline 3 applies.

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?

States a specific verb+resource (search the bundled Vidova Motion Canvas public API signatures and behavior guides, including Skia/SkSL shaders) and explicitly scopes it to a versioned, offline corpus. It also distinguishes itself from the sibling read_docs by stating it returns ids for read_docs, so an agent can tell search apart from fetch without opening either schema.

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?

Gives explicit when-to-use triggers (before guessing an unfamiliar API, after an API/type error) and an explicit alternative/follow-up path (ids for read_docs). It also sets boundaries — no repository or internet access, coverage is selected APIs, no match is not proof of absence — so the agent knows when this tool will and will not help.

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