knowledge_ingest

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

Annotations are all-false stubs (readOnlyHint: false, destructiveHint: false), so the description carries full burden and delivers: it discloses a real side effect ('successful write is logged to that subject's disclosure chain'), a hard authorization requirement (verified kb_promotion consent grant), and a non-obvious behavior (subject_id is never written, only checked). The pointer to the design doc is a bonus. No contradictions with annotations; this is a genuine value-add.

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 opening sentence is tight and front-loaded, and the param-signposting ('`subject_id` (guardian-consent seam):') is a good structural pattern. The second paragraph, however, is a dense wall of parenthetical-heavy prose that could be broken up or trimmed, and the doc path in the middle interrupts the flow. Efficient, but not maximally.

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 write tool with no output schema, no annotations, and no schema descriptions, the description covers the hardest conceptual piece (the consent seam) admirably and tells an agent the key side effect. But it leaves 5 of 6 parameters undefined, never clarifies the difference from near-sibling kb_ingest, and says nothing about the return value or duplicate behavior. Meaningful, but only partial coverage.

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% across 6 parameters, so the description must compensate. It does a stellar job on subject_id — explaining semantics, side effects, when to set it, when to leave it empty, and pointing to docs. But that is 1 of 6 parameters: app_id, content, source, domain, and tags remain completely unexplained, which is a real hole for an agent with zero schema help.

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?

Opens with a specific verb+resource: 'Add a knowledge atom to the Postgres knowledge base' — precise and unambiguous, followed by a useful behavioral qualifier about duplicate checking. However, it does not differentiate from the sibling tool `kb_ingest`, which appears to occupy nearly the same semantic space; an agent has no way to distinguish the two from the text.

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?

Includes implicit guidance — 'Check for duplicates first' signals a precondition, and the consent-grant requirement tells when a non-owner subject is allowed. But there is no explicit when-to-use vs when-not-to-use statement and no mention of alternatives like kb_ingest, store_put, or commitment_ingest. The guidance is useful but the reader must infer the usage boundary.

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