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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is covered; the description goes further by disclosing the two-stage pipeline, the mutual-exclusion constraint on image inputs, and a realistic latency budget (~5-15 s). It does not cover failure behaviour (e.g. no-match or unrecognised photo) or whether the uploaded image is retained, which is the only real gap for a read tool that ingests user media.

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 sentences, front-loaded with the trigger condition, then the mechanism, then the input constraint, then the fallback and latency note. Every sentence carries new information; the only slight cost is density, with the fallback instruction and latency note packed into the final sentences.

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 six-parameter, nested-object tool with an output schema and full annotation coverage, the description supplies everything the agent needs to decide and invoke correctly: trigger, alternative, input exclusivity, mechanism, and expected duration. Return-value detail is properly left to the output schema and filter semantics to the parameter descriptions.

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 the baseline is 3, but the description adds a genuinely non-schema constraint: exactly one of image_file / image_url / image_base64 must be supplied — the schema marks none of them required and cannot express that exclusivity. It does not describe the filtering semantics of max_price_eur or max_delivery_days, which the schema already handles well.

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 ('match a photo of a bouquet or flower arrangement') plus the concrete outcome ('find visually similar products available through Blumee'), and names its own mechanism (Pl@ntNet + vision model). An agent can distinguish it from search_flower_offers, which it explicitly names as the text-based fallback.

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 an explicit trigger condition ('when the user provides a photo... and wants to find visually similar products') and an explicit when-not/alternative path ('If you can see the photo but cannot pass it to this tool, call search_flower_offers with your own description instead'). That is a complete routing rule with no inference required.

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