ingest_canon

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

Annotations cover the safety profile (write, closed-world, idempotent, non-destructive), and the description adds genuine behavioral context beyond them: text is stored with derived hashes and line citations, external file/URL references are unavailable, and existing source IDs are immutable so editions require new IDs. The immutability rule is a meaningful trait not expressed by 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?

Three short, front-loaded sentences with no filler. The primary action leads, followed by scope limits and the ID rule, so nothing needs to be re-read.

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 2-parameter tool with annotations present and no output schema, the description covers the key storage behavior and the ID immutability rule. It falls short on the campaign_id parameter and the documents array semantics, which are undocumented everywhere.

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 0%, so the description must carry the load. It only alludes to the 'id' (immutable source IDs) and the text field; campaign_id, title, the array structure, and the 20-item cap are entirely unexplained in both schema and description.

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 (store/ingest) and resource (supplied story text), with the added detail that hashes and line citations are derived. This distinguishes it from the read-side siblings like read_canon and search_canon, though it never names them explicitly.

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 operational constraints (no file or URL access; new editions need new IDs) which imply how to call it, but does not state when to prefer this over alternatives such as create_branch or commit_turn. Usage is implied rather than explicit.

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