Compare the technology stacks of several websites

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

With no annotations, the description carries the burden of behavioral disclosure. It discloses the output format ('side-by-side table'), the quota impact ('Counts one scan per URL against the caller's plan'), and the allowed URL count ('2-25'). It doesn't mention failure handling or authorization, but the essential behavioral traits are present and it correctly implies a read-only scanning operation.

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?

Three concise sentences: the first states the core function, the second gives examples, and the third provides the sibling alternative and quota note. It is front-loaded and economical, though the example questions add length without new operational detail.

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 2-parameter tool with 100% schema coverage and no output schema, the description covers the essential pieces: what it does, the output shape, the quota, and the alternative tool. It doesn't address edge cases like invalid URLs, but that is beyond what an agent needs to make a correct call decision. The description is complete enough for safe and effective selection.

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 the baseline is 3. The description adds minor context by mentioning '2-25' websites and that bare domains are fine, but this largely repeats the schema's parameter descriptions. No new meaning is added beyond what the schema already documents, so the score stays at the baseline.

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 opens with a clear verb ('Scan') and resource ('2-25 websites'), and specifies the exact output ('side-by-side table of which technologies each one uses'). It explicitly distinguishes itself from the sibling batch_lookup by naming the alternative, so an agent can immediately tell them apart without opening either schema.

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 concrete example queries ('which of these prospects use HubSpot vs Salesforce?') that illustrate when to use this tool. It also states the exclusion case ('For the full per-site detail rather than a table, use batch_lookup'), providing explicit routing guidance.

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