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

With no annotations, the description carries the full burden and does real work: it discloses the authorization model (owner, office, or a worker assigned on the job), states the resulting state (draft, not submitted), and implies submitted forms are immutable via the copy-to-correct guidance. It omits idempotency, what happens on permission failure, and whether the mode parameters are mutually exclusive.

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 sentences, front-loaded with the action and target, then the mode options, then the permission/state constraints. Every clause carries information; nothing is decorative or restated from the schema.

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 not be described. Authorization, initial draft state, and mode selection are all covered for a 7-parameter creation tool. The remaining gaps are the unexplained signoff_required flag and the precedence when more than one source parameter (template vs. copy_from) is supplied.

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?

Top-level schema coverage is effectively zero, so the description must compensate — and it explains visit_id (one visit of the job), form_template_id (copy a template), copy_from_form_id (copy with answers), and name+fields, which is exactly the decision-relevant set. It leaves signoff_required completely unexplained, a boolean whose effect an agent cannot infer.

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 and resource ("Start a form") and immediately enumerates the three distinct creation modes: blank with fields, from a template, or copied from an earlier form. An agent can distinguish forms_start from forms_fill/forms_submit/forms_saveTemplate because it explicitly says the result "starts as a draft."

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?

Gives concrete conditional routing: use form_template_id to copy a template, copy_from_form_id to duplicate answers, which it calls out as "the way to correct a submitted form" — a genuinely useful decision hint. It does not name the nearest siblings (forms_fill, forms_submit, forms_listTemplates) or state exclusions, so it stops short of a 5.

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