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

With no annotations, the description carries the full burden and does most of the work: it discloses the validation-then-submit flow, that a confirmation email with a click-through link must be completed before any provider sees the data, and the exact consent scope ('up to three party wall surveyors'). It stops short of failure-mode behavior — what happens if validation fails, if the token is reused, or whether the token expires — which matters for a two-phase mutation.

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-loads the critical disambiguation ('NOT a purchase'), then splits the remaining content into Step 1 and Step 2, which mirrors how the agent must call it. The long consent string is unavoidable quoted legal text, not filler.

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 nested-object, no-annotation, no-output-schema mutation, the definition covers purpose, sequencing, return contents at each step, consent semantics, and the external verification gate. The remaining gap is recovery behavior when validation fails or a token is rejected, which an agent would have to discover by trial.

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 3 is the floor, and the description earns more: it explains that `answers` is keyed by field key from enquiry_fields and, crucially, gives `confirmation` a workflow role (absent in step 1, present in step 2 with the same answers and consent) that the schema's one-line token description only hints at.

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 ('Submits an enquiry to Party Wall Quotes') and immediately fences off the two most likely misreadings: 'NOT a purchase, NOT a guaranteed quote'. It also indirectly separates itself from the sibling read helpers by telling the agent that field keys come from enquiry_fields, so an agent can route correctly without opening both schemas.

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 a literal two-call protocol: step 1 with answers + consent=true to validate and obtain a summary/consent line/token, step 2 only after the person agrees, with the token added. Explicit preconditions, explicit gating, and an explicit stop condition are all present.

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