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

Beyond the readOnly/idempotent annotations it discloses privacy behavior ('no contact details, lead or email are sent'), a specific failure mode ('503 adviser_unavailable') with the required fallback ('offer contact@sp-insurance.ch'), and consent requirements. This is exactly the operational context annotations cannot 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?

Four short sentences, each carrying a distinct rule, with the primary action front-loaded before the error path and the alternative. Slightly dense with policy asides (optionality) that could be trimmed, but no sentence is 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?

Output schema exists so the returned link needn't be described; the description instead covers the cases the schema cannot — error signaling, fallback contact channel, consent gating, and the sibling alternative. Nothing an agent needs to invoke and handle this correctly is missing.

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 only 33%, but the description supplies the provenance that matters for the required parameter: comparison_id must come 'from the comparison'. The nested agent object and its aliases are already thoroughly documented in the schema, so little is left ambiguous, though the description says nothing about agent metadata semantics.

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 deliverable ('return a link') plus the concrete scenario ('client prefers to complete a website form'), and explicitly contrasts with the sibling request_adviser_contact. An agent can distinguish it from the comparison and contact-request tools without opening any 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?

Gives the positive trigger (client prefers a web form), the alternative and its condition ('client asks you to send the request in this conversation' → request_adviser_contact, with explicit consent), and an exclusion ('assistance is optional; clients may apply directly'). This is the full when/when-not/alternative triad.

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