Forms Legal templates

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

Goes beyond the annotations by disclosing a non-obvious side effect: each call is logged with the cited page path and a keyed hash of the anonymized user ID, with a link to the privacy section. Annotations already cover safety (readOnly, idempotent, non-destructive) and the description adds privacy/audit context that structured fields do not carry.

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 plus a short logging clause, with the scope restriction front-loaded before the exclusions. No filler; the privacy URL is the only extra token and it carries substantive information.

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?

The tool has an output schema, so return values need not be described. Scope, allowed formats, explicit exclusions, and the logging side effect are all covered, giving an agent everything needed to call it correctly and understand the consequences.

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%, and the format enum is already fully documented there; the description's list of formats merely restates the enum. The url parameter is not elaborated beyond the schema's own example, so this is the baseline case where the schema does the work.

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?

States a specific verb (cite) and a specific resource (a page on forms-legal.com), enumerates the supported output formats, and implicitly separates itself from the search_legal_templates sibling by scoping to citation generation. An agent can identify the tool's job without opening the 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?

Explicitly says 'Use this only to cite a page on forms-legal.com' and then enumerates what it must not be used for (articles, books, papers, court cases, other websites). Both the positive condition and the exclusions are stated, leaving nothing to inference.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, open world), yet the description still adds non-obvious behavior: searches are logged, IDs are keyed-hashed, search text is retained up to 30 days only on full misses, with a privacy URL. That is exactly the kind of disclosure annotations cannot carry, and it does not contradict them.

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?

Front-loaded with the usage trigger, then return shape, then exclusions, then the privacy note — a sensible order with no filler sentences. The final privacy sentence is long and denser than the rest, which slightly dilutes the otherwise tight structure.

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?

An output schema exists, so return values need no further explanation. Between the trigger conditions, the exclusions, the jurisdiction scope caveat and the logging disclosure, an agent has everything needed to decide whether to call it and what to expect.

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 schema already documents all four parameters; the description still adds real meaning by noting that the document name may be given in English or the local language, and by flagging the Quebec-vs-Canada separation that would otherwise trip up the country parameter. It stops short of any further hint on limit or language behavior.

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?

Specific verb and resource ('search' for 'legal form, contract, agreement, notice, letter or template') with explicit scope (36 countries, Quebec handled separately from Canada) and a clear statement of what comes back (template pages with link, referenced statute, short description). It does not name or differentiate itself from the sibling get_citation, so it falls short of a 5.

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?

Opens with an explicit trigger ('Use this when the user wants a legal form...'), then states hard exclusions: no legal advice, no judging clause validity or enforceability, no drafting custom documents. An agent cannot misapply this tool without ignoring a direct instruction.

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