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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description goes further by disclosing that results are limited to metadata and indicators, and, importantly, that the tool 'never visits the reported URLs' — a safety-relevant behavioral trait not present in the annotations. This additional context gives the agent confidence about side-effect-free execution and output scope.

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, each earning its place: the first states the primary action and time window, the second clarifies output scope and a safety property. The description is compact, front-loaded, and contains no filler. Every clause adds value for an agent evaluating whether to invoke the tool.

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 simple one-optional-parameter list tool with rich safety annotations, the description is nearly complete. It explains the time window, output class ('bounded metadata and indicators'), and a behavioral guarantee (not visiting URLs). However, without an output schema, it does not detail the exact fields or structure of the returned metadata/indicators, so an agent cannot know precisely what keys to expect. This minor gap keeps it from a 5.

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 input schema already provides a description for the only parameter (limit) with default and max values, so schema coverage is 100%. The tool description adds no extra detail about the parameter syntax, format, or edge cases. Thus a baseline 3 is appropriate because the schema does the heavy lifting; no ambiguity remains about what limit means.

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 ('List') and resource ('recent malware-distribution URLs added to URLhaus'), and adds a concrete scope: 'rolling three-day window.' It clearly distinguishes itself from the lookup-specific siblings (e.g., urlhaus_lookup_host, urlhaus_lookup_url) by focusing on recent additions rather than targeted lookups. No ambiguity about what the tool does or what it returns.

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 provides clear context for when to call this tool ('recent URLs added in rolling three-day window'), and the sibling names (urlhaus_recent_payloads, urlhaus_lookup_*) hint at alternative purposes. However, it never explicitly says 'Use this for recent URL lists; use urlhaus_lookup_url for a specific URL' or names exclusions. Usage guidance is therefore implied rather than clearly stated.

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