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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description still adds genuine context beyond that: 'Nothing is sent: the person opens the link, checks the form and sends it themselves,' which tells the agent the server performs no submission and the human must complete the handoff. Link expiry or reuse behavior is not covered, which keeps it off a 5.

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 short sentences, front-loaded with what is returned, then the usage condition, then the side-effect caveat. Every sentence carries distinct information and none repeats the title or the annotations verbatim.

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 the link return value needn't be explained, and the annotations cover the safety profile. The remaining gap is the four undocumented parameters and the mild tension between 'commercial or multi-unit building' and enum values such as 'portfolio' and 'other'; otherwise an agent has what it needs to call this 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 coverage is 43% across seven parameters; only building, type and note carry descriptions in the schema. The description adds the unifying principle that every field is a prefill of 'the details the person has given,' which implies none should be guessed or invented, but it does not clarify the role enum (which includes 'home') or the organisation/email fields. Baseline 3 is appropriate here.

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 concrete verb and artifact — 'Returns a link to the Moyne Ross request form' — plus the scope ('one actual commercial or multi-unit building') and the prefill behavior ('with the details the person has given filled in'). No sibling tool produces a request link, so an agent can separate this from get_sample_strategy or working_with_moyne_ross without opening a 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?

It gives an explicit trigger ('Use only when the person asks to request a Capital Strategy') and an explicit input constraint ('only with details they have provided'), which is exactly the guardrail needed against fabricated prefill values. It stops short of naming a sibling to use instead when the person merely wants information about Capital Strategy, so alternatives must be inferred.

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