capture

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

With no annotations provided, the description carries the full behavioral burden and does so well. It discloses that captures are project-local by default, that secrets are redacted before storage, that messages are flattened for search while originals are retained, and that atoms affect recall behavior. This is substantial beyond the schema.

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 compact and front-loaded: it opens with the core purpose, then usage timing, content options, scoping default, and the critical global-memory caveat. Every sentence contributes either behavioral, scoping, or usage information without fluff.

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 17-parameter tool with no output schema and no annotations, the description covers the essential aspects: when to call, what to store, project-local behavior, the global exception, redaction, and the messages/atoms interaction. Remaining gaps are minor—it does not mention output behavior or the isolation parameters (task_id, team_id, user_id, agent_id)—but the schema covers those.

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 100%, so the baseline is 3. The description adds meaningful parameter-level context beyond the schema: the semantics of session_key='global', the content-versus-messages relationship, and the behavior of atoms. This elevates the score, though many parameters like tags, metadata, and verified are left to 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 names a specific action ('Store a decision, a learning, or a task outcome to memory') and gives concrete examples of when to call it. It is clear and distinguishes capture from retrieval-oriented siblings like recall and search, but it does not explicitly differentiate from record_outcome or knowledge_create, so it misses the top score.

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 gives explicit usage timing: call after completing a non-trivial task, making a decision, or fixing a bug with a known root cause. It also gives a strong exclusion—global memory should only be used when the user explicitly asks—and tells the agent exactly how to enable it via session_key='global'. It does not name alternative tools, so it stops short of a 5.

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