cls_ingest

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

No annotations are provided, so the description carries the full burden. It only states that the tool ingests signals and that the brain learns from every commit and CI run, but it does not disclose any behavioral traits such as idempotency, error handling, rate limits, or potential side effects like overwriting data.

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 concise (two sentences plus an enumeration) and front-loads the core purpose. Every sentence provides essential information without redundancy.

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 lack of output schema and annotations, the description covers the tool's functionality well but does not explain what the tool returns (e.g., success/error response) or handle edge cases. However, for a simple ingestion tool, it is largely complete.

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%, but the description adds value by detailing the expected structure of the payload for each source type (e.g., git_commit: {message, sha?, files?, diff?}). This goes beyond the generic schema description and helps agents construct correct payloads.

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 specifies the tool's purpose: ingesting learning signals without explicit session_end calls. It lists three specific sources (git_commit, ci_outcome, ide_diagnostic) and distinguishes itself from sibling cls_install_hooks by mentioning installation for automatic ingestion.

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?

The description implies when to use this tool (for continuous learning stream) and references cls_install_hooks as a prerequisite for automatic ingestion. However, it does not explicitly state when not to use it or compare to alternatives like session_end or global_learn.

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