cls_ingest

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

With no annotations provided, the description carries full burden. It explains that ingestion happens without session_end calls and lists each source's data fields. However, it lacks details on side effects, idempotency, error handling, or whether it is destructive.

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 somewhat verbose and could be more concise. While front-loaded with core purpose, it includes redundant phrases like 'install automatic ingestion' and 'brain learns from every commit' that could be streamlined.

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 three required parameters and no output schema, the description covers the purpose and source details adequately. However, it lacks information on return values, error conditions, or success indicators, leaving gaps for an agent to fully understand the tool's behavior.

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?

The schema already provides descriptions for all parameters and nested objects (100% coverage). The description adds contextual meaning by elaborating on each source type and its data structure, which helps the agent understand usage beyond 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 purpose: ingesting learning signals from specific sources (git_commit, ci_outcome, ide_diagnostic) without requiring explicit session_end calls. It distinguishes from siblings by mentioning automatic ingestion and hook installation, and ties into the broader system.

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 explains when to use the tool (to ingest learning signals from the listed sources) and hints at prerequisites (install hooks via cls_install_hooks). However, it does not explicitly state when not to use it or compare with alternatives like session_end.

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