Voix contact

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds genuinely new behavior: it sends nothing, it only draws the form, it hands submission responsibility to the person, and it reports a reference afterwards. It also imposes a prefill honesty constraint not captured anywhere else.

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 paragraphs, front-loaded with the action, then the routing rule, then the no-send guarantee and duplicate-call warning. Every sentence carries decision-relevant 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?

An output schema exists, so return values need no explanation, yet the description still notes the form returns a reference. Safety is covered by annotations and the tool's side-effect-free nature is spelled out, leaving no material gap for an agent.

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 per-field formats and enums are already documented (baseline 3). The description adds real semantic guidance beyond the schema: prefill only what the person actually stated and never invent name, email, or budget values.

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 first sentence states a precise verb and resource: show an editable contact form, prefilled with known details. It is unmistakably distinct from submit_contact_form, which the description names directly.

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 routing rule ('use this in place of submit_contact_form whenever you can show interactive content') and an explicit anti-pattern ('do not also call submit_contact_form for the same enquiry'), including the reason: the form sends itself and returns a reference.

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 mark this as openWorld, non-idempotent, destructive and non-read-only. The description adds real context beyond that: the submission lands in the team's notifications, a human replies by email within ~two business days, and successful calls should not be retried. It stops short of stating that a sent message cannot be recalled or corrected, which is the main destructive consequence.

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 action, then triggers, then outbound behavior, then calling constraints — a sensible ordering with no filler in the middle. One sentence is wasted because it is inaccurate: 'There is no other tool here... this is the only thing this server does' contradicts the existence of draft_contact_form.

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 7-parameter submission tool with full schema coverage, an output schema and rich annotations, this covers everything an agent needs: purpose, when to send, data-provenance constraints, and what happens after sending (human reply, ~2 business days). Return values need not be explained because an output schema exists.

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 carries the field-level semantics and a 3 would be the baseline. The description goes further by imposing a cross-parameter policy the schema cannot express: supply only real, person-confirmed values for name, email and message, and never estimate budget or scope on the user's behalf.

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 (send an enquiry via the website contact form) and names the recipients (Voix / LogicBomb Media), so the action is unambiguous. However, the claim 'There is no other tool here — ... this is the only thing this server does' is factually wrong given the sibling draft_contact_form, and the description never differentiates itself from that sibling.

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 strong positive triggers (start a project, request a quote, book a demo, pricing, partnerships) and clear exclusions policy ('Do not invent contact details, do not submit on a hunch... send one per enquiry rather than retrying a call that already succeeded'). It does not, however, tell the agent when to use draft_contact_form instead, which is the obvious alternative in this server.

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