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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds substantial context beyond those: what each entry contains (screenshot, one-sentence summary, tags, builder credit), result ordering ('newest matches first'), and the editorially-curated, non-ranking nature of the corpus. Return ordering and content composition are genuine behavioral disclosures.

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?

Dense but front-loaded: the corpus is described first, then filters, then ordering, then usage and exclusions. It is longer than average, yet nearly every clause carries information an agent needs; only the repeated examples could be trimmed.

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 10 params, an output schema, and full annotation coverage, the remaining missing pieces are usage scope and corpus semantics, both of which the description supplies explicitly, including what it does not do. An agent has everything it needs to call and interpret this tool correctly.

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 coverage is 100%, so the schema already documents every parameter with examples and enums. The description adds only a high-level enumeration of filter dimensions ('trade, region, style, colour, platform, conversion features or typeface') and a free-text note, which largely restates what the schema supplies. Baseline 3 is correct.

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 states a specific verb and resource ('Search Handsome Local, a hand-picked gallery of real websites for trades and home services businesses'), specifies the domain (UK/US trades), and distinguishes itself from siblings get_website (detail fetch) and list_filters (facet enumeration). An agent can identify exactly what corpus this searches.

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?

It gives clear usage context ('Use it for visual references when designing or building a website for a tradesperson') and explicit exclusions ('It does not rate or rank sites and it covers the trades listed only'). It does not explicitly name get_website as the tool to use for full details, so it stops short of full alternative routing.

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