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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=true, covering the safety and openness profile. The description adds useful context beyond those: it discloses pagination behavior, the credit line billing fields returned, and the sandbox environment filter. It does not describe rate limits or ordering guarantees, but for a read-only search with rich annotations, this is solid extra context.

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?

The description is well-organized with markdown headers ('Overview', 'When to Use', 'What You Get', 'Request Body', 'Quick Start'), which front-loads the purpose effectively. However, it is longer than necessary for a tool with 4 parameters and full schema coverage, repeating field definitions already in the schema and including a 'Quick Start' section that duplicates the request body details. The structure is clear but not tight.

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 read-only search tool with full schema coverage and rich annotations, the description covers the essential aspects: what it searches, how pagination works, and what the response includes (data array, success, pagination fields, credit line billing). No output schema exists, so the 'What You Get' section fills a real gap. It is largely complete, though it could mention whether results are ordered or how to handle empty result sets.

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 already documents all four parameters. The description largely repeats those definitions ('query (required) - Text to search for', 'page - Zero-based page index', 'rowsPerPage - Number of results per page', 'sand_box - Filter by environment'), adding only minor examples like '(e.g. "false" for production)'. Baseline 3 is appropriate when the schema carries the full load.

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 specific verb and resource: 'Search for bookings by free-text query', and specifies which fields are matched (guest names, booking IDs, hotel names, and other booking-related fields). It clearly distinguishes itself from get_bookings or listBookings by emphasizing free-text search rather than filtered retrieval. However, it does not explicitly name a sibling as an alternative, so it falls short of a 5.

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?

The 'When to Use' section provides contexts like 'Admin or support lookup' and 'Text search', which imply usage scenarios but stop short of explicitly stating when to prefer this tool over get_bookings or listBookings. No exclusions or alternatives are named, leaving the agent to infer the appropriate selection criteria on its own.

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