usage_report

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint. The description adds critical behavioral details: data sources (.claude, .codex), client-specific coverage (Cursor not locally exposed), and that it never indexes. No contradictions.

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 information-dense but somewhat long (multiple sentences listing layers). It could be more concise by grouping details, but it avoids repetition and is well-organized.

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 no output schema, the description covers the report's contents and data sources. It lacks error scenarios or restrictions, but for a read-only diagnostic tool, it is sufficiently 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 coverage is 100%, so the baseline is 3. The description adds minimal context beyond schema (e.g., 'default 20' for refs) but does not elaborate on each parameter's meaning. Adequate but not exceptional.

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 tool's purpose: 'Per-project tool-usage + token report.' It enumerates specific data layers (codehelper output, model tokens, verification outcome, recent-call trail) and distinguishes it from siblings like log_read or db_query by focusing on usage analytics.

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 this tool is for diagnostic/audit use cases ('never indexes', 'read-only'). It does not explicitly state when to avoid it, but the purpose is clear enough for an agent to decide.

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