Blumee — flower delivery comparison (Germany)

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

Annotations already declare readOnly/idempotent/non-destructive, lowering the bar. The description adds genuine behavioral context: the first cursorless call returns available_values enumerating valid flower/colour/occasion/shop values. That's a real trait not encoded elsewhere.

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?

Three tight sentences with zero padding. Filters, the available_values note, and the sibling redirect are each front-loaded in a single clause.

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?

The description covers filtering, paging via cursor, and the available_values discovery mechanism. An output schema exists, so return-format explanation isn't needed. Minor gap: it doesn't say whether cursor paging preserves filters.

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 parameter meaning is already fully documented. The description's mention of price range and delivery time mirrors schema content rather than adding syntax, so baseline 3 applies.

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+resource ('List offers') and enumerates the exact filterable attributes. It also names the sibling 'search_flower_offers' for free-form wishes, so an agent can pick it apart from alternatives.

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 explicit example queries ('what does shop X have', 'cheapest tulips') and explicitly routes free-form wishes to search_flower_offers. The when-to-use boundary is concrete, not implied.

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

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds useful behavioral context beyond that: what content is returned (all images, delivery terms) and that it surfaces same_bouquet_offers for price comparison, which is non-obvious. No rate limits or failure modes are mentioned.

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?

Front-loaded with the core action, then the payoff (cross-shop comparison), then the usage rule. The first sentence is dense with a parenthetical field list, but no sentence is wasted.

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 single-parameter read tool with an output schema and full annotation coverage, the description supplies everything an agent needs: when to call it, what it returns, and the comparison value it unlocks. Nothing material 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 description coverage is 100% and the single offer_id parameter is fully documented in the schema as a UUID returned by search. The description's 'by id' adds nothing beyond that, so the baseline 3 for high-coverage schemas applies.

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 ('Get full details of one offer by id') and enumerates exactly what comes back: description, images, size, species, delivery terms, plus cross-shop price comparisons. An agent can immediately tell this is the single-offer drill-down, distinct from catalog browsing or search.

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?

Explicitly says 'Use after a search when the user asks about a specific offer,' which positions it in a workflow after search_flower_offers. It does not name a sibling tool by name or state when-not-to-use, so it stops short of a 5.

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

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.

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds language-agnostic query handling and a return summary (ranked offers with price, shop, delivery time, links), but the return shape is already covered by the output schema, so incremental behavioral disclosure is modest.

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?

Front-loaded with the core action and usage triggers, and tightly written. The final sentence restating return contents is largely redundant given an output schema exists, costing a little efficiency.

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 10-parameter tool with 100% schema coverage, full annotations and an output schema, the description covers everything an agent needs that structure does not: when to invoke, the photo fallback path, and the query-language convention.

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 baseline is 3; the description adds a meaningful calling convention beyond the schema by telling the agent to pass free text as `query` in any language and to add structured fields only when known, which clarifies the relationship between query and the structured filters.

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?

Specific verb+resource (find real flower bouquets and potted plants for sale) plus an explicit trigger domain (user asks for flowers in words). It also distinguishes itself from the sibling match_bouquet_photo by stating the condition under which it substitutes for it.

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 concrete usage triggers (flower type, colour, occasion, recipient, budget, delivery deadline) with worked examples, and explicitly states the alternative path: use this when match_bouquet_photo cannot receive the file, describing what is visible in the photo instead.

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