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

Annotations only declare a safe read (readOnlyHint, destructiveHint false), yet the description adds substantial behavioral context: media routing through Sedna's CdnManager, missing CDN media returned as empty rather than a legacy DB URL, MCP Apps inline gallery vs. raw URLs, and the omission semantics for optional length/beam. This is well beyond what the annotations convey.

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 purpose and post-search positioning are front-loaded, and most sentences carry distinct behavioral content (empty-vs-legacy URL rule, length/beam omission, booking_detail exclusion). It runs long with some density, but little is redundant given the absence of an output schema.

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?

There is no output schema, so the description must carry the return shape itself, and it does: media.header, media.photos, media.plans, media.images, media.videos and media.documents. Combined with the rendering fallback and the explicit statement of what it does not return, an agent has everything needed to call and interpret it.

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 baseline is 3; the schema already documents id_boat, language, and sheet_type thoroughly. The description's 'id_boat must be copied exactly from search_boats' largely restates the schema's 'Never guess it,' adding only marginal value.

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 gives a specific verb and resource: return yacht details plus CDN-backed public URLs for yacht media. It also positions itself explicitly as "the primary tool to call after search_boats," which distinguishes it from siblings like booking_detail and compare_boats.

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 names the trigger conditions (customer asks to see photos, gallery, plans, videos, documents, or layout/capacity/dimensions/crew/itinerary) and the alternative for pricing (use booking_detail for date-specific prices, extras, availability). It even gives a negative guideline: do not exclude a yacht or ask for length/beam absent an explicit customer requirement.

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