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

Annotations already declare readOnlyHint true and destructiveHint false, but the description adds critical context: draft is AI-assisted, Telegram URL is for manual send, never contacts anyone, missing details returned as questions, reference_id expires after 30 minutes, and never invent a table price or discount. This goes well beyond what annotations provide.

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?

Description is front-loaded with core purpose, then constraints and workflow. It is appropriately sized for a complex 16-parameter tool, though slightly dense; could be bulleted for clarity. Every sentence adds useful 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?

Covers purpose, safety, key behavioral rules, and some workflow (show draft, missing details). But with 16 parameters and near-zero schema descriptions, it leaves many parameters unexplained and does not describe the return shape (no output schema) beyond 'returns questions' and 'draft'. Adequate but with clear gaps for an agent to call correctly without guessing.

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 only 6% (only origin has a note), so the description must compensate. It adds meaningful detail for reference_id (source, matching, 30-min expiry) and mentions budget/country missing details, but does not explain the other 13 parameters (e.g., cut, polish, symmetry, fluorescence, budget_scope, budget_currency, destination_country) beyond their enum values. Most parameter semantics are left to the schema names.

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 'Prepares' and outputs 'draft marked as AI-assisted' and 'Telegram URL' for client review and manual send. Explicitly says it never submits, reserves, buys, or contacts anyone, distinguishing it from transactional tools and clarifying that it is a preparation step. Names estimate_rapaport as the source for reference_id, indicating sibling relationship.

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?

Instructs to show the full draft to the client before opening Telegram, and that missing budget/country details are returned as questions. Indicates reference_id must come from estimate_rapaport and match the stone, implying that tool should be used first. However, no explicit when-not-to-use or alternatives beyond estimate_rapaport are stated.

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