log_event

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

With no annotations at all, the description carries the full behavioral burden and does disclose two non-obvious traits: arguments are stored with secrets masked, and the call returns the stored record including seq and hash. It does not say whether the log is append-only, whether entries can be amended or deleted, or what happens to orphaned "pending" rows, which matters for an audit tool.

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?

Front-loaded verb+resource sentence, then a Who/What/Why/Approval/Outcome skeleton that maps directly onto the schema fields. Every line adds a distinct constraint or example; nothing is repeated from the title or padding.

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 12-parameter mutation tool with zero annotation coverage this is substantially complete: it explains the two-phase pending-then-outcome pattern, the approval taxonomy, secret masking and the returned identifiers, and an output schema exists so return values need no further prose. The remaining gap is the unexplained tags, run_id and result_summary fields plus no note on write permissions or log immutability.

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 has to compensate, and it does for most fields: agent_id is defined as the agent's stable name, model gets an example value, reason is constrained to one plain sentence, and approved_by/approval_rule are tied to their respective approval modes. Three parameters (tags, run_id, result_summary) get no explanation anywhere, which keeps this below a 5.

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?

"Record one agent action in the logbook" states a precise verb (record), a precisely scoped resource (one agent action) and the destination (logbook). It is immediately distinguishable from siblings verify_logbook, recent_events and export_logbook, which read, verify or export rather than append.

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 Outcome line gives real workflow guidance: log with "pending" before acting, then log the same action again with success/error/escalated. The Approval line similarly prescribes which approval mode pairs with which field. It never states when not to log, or why one would pick this over recent_events, 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.