Scan Claude Code logs

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

With no annotations provided, the description fully discloses behavior: it reads token counts and metadata, never message content, is idempotent, and safe to run repeatedly. It could briefly mention permission requirements (e.g., read access to ~/.claude/projects), but overall good transparency.

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?

Three sentences with no wasted words: first sentence states purpose, second adds scope and constraints, third confirms idempotency. Information is front-loaded.

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 a simple tool with 1 optional parameter and no output schema, the description covers purpose, input, behavioral constraints, and safety. Sibling tools are sufficiently distinct, so no further context is needed.

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% for a single optional parameter 'dir'. The description adds the default directory path (~/.claude/projects) and the meaning 'override the Claude Code projects directory', providing more context than the schema alone.

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?

Description clearly states the verb 'Backfill', the resource 'exact AI usage from Claude Code's local session transcripts', and scope 'reads only token counts + metadata, never message content'. It differentiates from siblings like analyze_efficiency by focusing on raw log scanning rather than analysis.

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?

Description explains when to use (backfill exact AI usage) and emphasizes it is idempotent and safe to run repeatedly. It specifies what it reads (token counts + metadata) and crucially what it does not read (message content), but does not explicitly mention when not to use or alternatives among sibling tools.

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