document_delete

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

Annotations already signal destructive behavior, but the description adds crucial context: the deletion is scoped to one document's chunks, confirmation requires an exact doc_id match, the tool is disabled in read-only mode, and it must only be used after explicit user confirmation. No contradiction with the 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?

Every sentence earns its place. It front-loads the core action and scope, then adds the safety constraints in a compact and readable way. No redundant filler.

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 destructive, three-parameter tool, the description conveys scope, safety guards, preconditions, and when and when not to invoke it. An output schema is present, so not describing the return format is acceptable. The agent has everything needed to safely choose and call this tool.

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 0%, so the description must compensate for the bare parameter names. It explains confirm_doc_id's role as a guard requiring an exact match with doc_id, and it clarifies that the deletion acts on chunks of a single document within a collection. It does not elaborate on the collection parameter, but its meaning is recoverable from context and the param name.

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 ('Deletes') and resource ('every chunk belonging to one source document from a collection'), and clearly distinguishes this from collection-level deletion. The phrase 'every chunk belonging to one source document' makes the tool's exact scope immediately obvious, and 'without touching the rest' removes ambiguity.

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?

Explicitly tells the agent when to use the tool: only when the user has explicitly confirmed deletion. It also states when not to use it: in read-only mode, and when confirm_doc_id does not exactly match doc_id. This is strong usage guidance for a destructive operation.

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