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

Annotations already declare readOnly/idempotent/openWorld, and the description adds substantial context beyond them: which archives are queried, that diffing is on readable text not markup, the max_gap_days fallback behavior, and the exact no_capture and changed:false outcomes with their reasons. This is precisely the behavioral detail an agent needs to interpret results.

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?

Front-loaded with the core question, then moves through mechanics, edge cases, and use cases in a logical order. Dense but every sentence contributes; slightly long but not padded.

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?

With no output schema, the description carries the return-shape burden and does so fully: diff segments, similarity score, both capture timestamps with gaps, and status values for the no-capture case. An agent knows what it will get back.

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 baseline is 3; the description adds meaning by explaining that dates resolve to the nearest capture within max_gap_days and reporting capture-timestamp gaps. It complements rather than repeats the schema field descriptions.

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?

Opens with a specific question form and names the exact resource and operation: resolving archived captures and returning a text-level diff. It clearly distinguishes itself from sibling archive_evidence and resolution_diff by specifying text-level diffing and multi-archive resolution.

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 typical uses (privacy policy, ToS, pricing changes, whether a statement was on a page) and states the semantic boundary that markup diffs are out of scope. It does not name sibling tools or say when to prefer archive_evidence instead, so it falls short of a full 5.

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