maritime_audit_links

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

Since no annotations are provided, the description carries full burden. It reveals that wreck links use exact matching (precision=1.0) and CLIWOC links use fuzzy matching. It also describes output format (JSON/text with metrics). No mention of destructive actions or permissions, but it implies read-only audit.

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?

Description is well-structured with a summary, details, and tips. Concise yet informative. One minor point: the 'Returns' section could be merged with the summary, but overall effective.

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?

Covers return values (precision/recall, confidence distributions) despite no output schema. Includes example targets for LLM guidance. Single parameter fully explained. No gaps in context for usage.

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?

The only parameter (output_mode) is described in the Args section with default and valid values ('json' or 'text'), adding meaning beyond the schema which only shows a default. Schema coverage is 0%, so description compensates well.

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 explicitly states the tool audits cross-archive link quality against known ground truth, with specific details on precision/recall evaluation for different link types (CLIWOC tracks, wrecks). It clearly distinguishes itself from sibling tools like search or aggregate functions.

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 tips for when to run (after data updates) and targets (200+ CLIWOC fuzzy matches, mean confidence > 0.7). Does not explicitly state when not to use, but context makes it clear this is a specific audit tool.

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