corpus_add

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

Beyond the annotations (destructiveHint=true), the description discloses concrete behavioral details: 'skips an already-indexed video by default', 'force_reembed=true deletes and replaces that video's existing local chunks and vectors', and 'may contact YouTube'. It also states the return value ('indexing status and chunk count'), which is useful since no output schema is provided. No contradiction with annotations.

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 three sentences, each serving a purpose: first states what it does, second gives usage context (sequence and default behavior), third discloses side effects and return info. No redundant or vague language.

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's moderate complexity (3 params, 2 required, no output schema), the description covers the essential aspects: purpose, prerequisite (corpus_create), default behavior, side effects, external interaction, and return value. It is complete enough for an agent to select and invoke the tool correctly without ambiguity.

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 baseline is 3. The description adds extra meaning for 'force_reembed' by explicitly explaining that it 'deletes and replaces that video's existing local chunks and vectors', which is beyond the schema's 'Re-embed even if already indexed'. It also clarifies the default skip behavior, providing context not fully captured in 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 states the tool's function: fetching a transcript, chunking it, and storing local embeddings in an existing corpus. It uses a specific verb 'add' (implied) and distinguishes itself from sibling tools like youtube_get_transcript and corpus_search by focusing on indexing into a corpus.

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 says 'Use this after corpus_create', giving a clear sequencing context. It also explains the default skip behavior and the force_reembed alternative. However, it doesn't explicitly name alternatives or exclusions (e.g., 'if you just need a transcript, use youtube_get_transcript'), so it falls short of the highest benchmark.

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