Recommend headline tools

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

The description discloses key behavioral traits beyond annotations: it reads the audit log, uses a capped lookback window (default 7, max 90), groups by capability bucket, and returns a diagnostic when the audit subsystem is off. The annotations already declare readOnlyHint=true, and the description reinforces this by describing a read-only operation. It adds value by detailing the exact return structure and edge cases.

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 well-structured and front-loaded: the first sentence captures the core purpose. Subsequent sentences detail behavior, output structure, and an example. It is moderately concise—every sentence adds information without redundancy. The example at the end is helpful and fits within the description length.

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 that the input schema is simple (3 optional parameters with defaults), annotations are present (readOnlyHint), and output schema is partially described in the description, the description is highly complete. It covers all necessary details: key parameters, default behaviors, edge cases (audit off), and the full return structure (including nested objects). No significant gaps remain.

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 has 33% description coverage (only 'database' is described), but the description adds meaningful details for all parameters: it explains the purpose, default values, and constraints (e.g., lookback_days capped at 90, top_n default 6). This compensates for the schema's lack of parameter descriptions and provides clear semantics for agent invocation.

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 specific action: 'Empirically curate describe_self's per-bucket headline_tools from the audit log.' It uses a precise verb+resource structure ('curate...headline_tools') and distinguishes itself from sibling tools by explicitly referencing the per-bucket headline tools context and the describe_self scope.

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 get a recommendation for updating headline tools) and what the output is (a reviewable recommendation, not auto-applied). It also covers the special case when the audit subsystem is off. However, it does not explicitly state when not to use it or provide alternatives among the many sibling recommend_* tools.

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