batch_analyze

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

With no annotations provided, the description carries the full burden. It discloses read-only nature: 'Read-only: reads every matched file (capped by maxFiles) and makes one LLM call per file (parallel by default).' It also explains the behavior of aggregateResults and return shapes for all modes, including edge cases like empty pattern match. This is rich, honest behavioral context.

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 dense but every sentence adds value. It front-loads the core purpose, then usage guidance, alternatives, behavioral notes, and return shapes. There is no fluff or repetition. The structured breakdown of return shapes is efficient and clear.

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?

This is a complex tool with two output modes, yet the description fully covers purpose, usage, behavioral traits, and return shapes for both modes and the empty-file case. No output schema exists, so the description's detailed return shape specs are essential and complete. The sibling differentiation is also covered.

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 67% with some param descriptions already present. The description adds meaning beyond the schema by explaining the critical aggregateResults flag's effect on output shape, and mentions the maxFiles cap. It also provides examples for filePatterns in the schema, but the description itself doesn't repeat all options. Slightly above baseline because it compensates for the missing output schema and clarifies key parameters.

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 function: 'Run the SAME question against a glob of files, then aggregate the findings into one cross-file summary.' It distinguishes itself from siblings by explicitly naming alternatives: 'For ONE file, use analyze_file (cheaper). For NL search without a known file set, use explore.'

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?

Provides explicit use cases: 'codebase-wide audits', 'per-feature reviews', 'pre-merge sweeps'. Also gives explicit exclusions and alternatives: 'For ONE file, use analyze_file' and 'For NL search without a known file set, use explore.' This meets the 'when/when-not/alternatives' criterion perfectly.

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