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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description repeats 'Read-only' which is redundant but does not contradict. It adds valuable behavioral context beyond annotations: the tool flags dangerous entries (absolute paths, .., symlinks, encrypted entries, duplicate names, bombs) and is intended to run before zip_extract. This enriches the agent's understanding of what the tool does at runtime despite the annotation coverage.

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 two sentences plus a short fragment: it front-loads the core action and safety flags, then gives usage guidance. The standalone 'Read-only.' is redundant with annotations and could be folded in, but it is short and does not bloat the text. Overall it is tight and efficient with no filler, only the repeated annotation costs a small deduction.

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 list tool with no output schema, the description adequately conveys what the tool returns at a high level (entries with sizes/ratios plus danger flags) and notes that totals always cover every entry (in the limit parameter description). Combined with annotations covering safety, the description is sufficient for an agent to invoke it correctly before extraction. It could be more explicit about the exact return structure, but that is not essential for a listing operation.

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 100%, so each parameter (path, limit, patterns, max_ratio) already has a clear description. The main description mentions 'sizes and ratios' which relates to output and max_ratio, and 'flag what is dangerous' connects to the safety checks, but it doesn't add new semantic nuance beyond the schema. Baseline 3 applies because the schema carries the parameter semantics.

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 uses a specific verb and resource: 'list an archive's entries with sizes and ratios' and clearly defines the uniqueness via safety flags (absolute paths, .., symlinks, encrypted entries, duplicate names, bombs). It also names the sibling zip_extract for context, which differentiates it from a plain listing tool. The purpose is unmistakable and distinguishes the tool from the sibling set.

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 gives explicit usage direction: 'Run it before zip_extract.' This tells the agent exactly when to invoke it as a pre-extraction safety check. However, it does not mention alternatives (e.g., zip_files) or state when not to use it, so it falls short of full 5 because exclusions and alternative routing are absent.

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