knowledge_ingest

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

With no annotations, the description carries the full burden. It discloses several behavioral traits: duplicate checking, logging to the subject's disclosure chain, and that subject_id is opaque and never written to the KB. However, it doesn't specify what happens on duplicate (e.g., error vs. skip) or describe the return value, keeping it from a 5.

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 front-loaded with the main action and duplicate check, then provides a detailed but necessary explanation of the complex subject_id parameter. Although the subject_id paragraph is lengthy, it earns its place due to the parameter's non-obvious semantics and consent requirements.

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?

The description covers the main action, duplicate check, logging, and consent requirements, which is substantial. However, it lacks details on duplicate handling (whether it errors or returns existing atom) and does not mention return values, which is relevant given no output schema. These gaps prevent it from being fully 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 description coverage is 0%, so the description must compensate. It thoroughly explains subject_id, including the guardian-consent seam and consent grant, but does not add detail for the other five parameters (app_id, content, tags, domain, source). This partial compensation for the most complex parameter justifies a mid-range score.

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 states 'Add a knowledge atom to the Postgres knowledge base' with a specific verb and resource, and includes 'Check for duplicates first' for additional clarity. It does not explicitly differentiate from sibling tools like kb_ingest, so it doesn't reach a 5.

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 usage for adding knowledge atoms and includes a duplicate-check guideline, but it doesn't mention alternatives or exclusions. The detailed subject_id guidance is parameter-specific rather than tool-selection guidance, so usage context is present but not fully explicit.

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