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

Annotations already declare read-only, idempotent, non-destructive, and closed-world. The description adds behavior beyond that: the 64-bit SimHash algorithm, word shingles, and the crucial calibration that unrelated texts score around 50%, not 0%.

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?

Two sentences, no waste. Front-loads the algorithm and core use case, then adds the essential score interpretation.

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?

No output schema exists, but the description explains what each input mode returns (a hash for one text, a comparison score for two) and how to interpret that score. That is complete for a single-parameter pure function.

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 already documents the sole parameter at 100% coverage, including the 1-vs-2 text modes and 200k char limit. The description repeats the input modes without adding syntax beyond what the schema provides.

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?

Name and description together state a precise operation: near-duplicate detection via 64-bit SimHash over word shingles. It clearly distinguishes this from every sibling (none of which compute text similarity) and explains the two input modes.

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 clear context for when to use it (near-duplicate detection, paraphrased or lightly edited copies) and how to invoke each mode (1 text for hash, 2 for compare). It does not state explicit exclusions or alternatives, but given no sibling overlaps, the guidance is adequate.

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