BIDON - Parts & Materials Buying/Selling AI Agent (비드온)

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: results are manufacturer-catalog models with specs, each part reports how many BIDON sellers list it and whether BIDON supplies it directly, and stocked models are ordered first. No output schema exists, so this return-shape disclosure is valuable; only pagination/limits are unaddressed.

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 condition and alternative, then organized with semicolons so each clause maps one category to its filter fields. Dense and long, but nearly every clause carries non-redundant information; it reads as one extended sentence where shorter bullets would scan better.

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 an 18-parameter, one-required-param tool with no output schema, the description covers trigger, category semantics, return contents (vendors, direct-supply flag, stocked-first ordering) and the handoff to lookup_part. Nothing an agent needs to call it correctly 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 every field is documented, so the baseline is 3. The description goes further by grouping parameters by category (power supplies by output voltage and minimum power/current; breakers by type, poles, rated current; cables by ampacity, cores, installation; sensors by size, distance, mounting, output, contact, connection), which is the mapping the flat schema does not express.

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 ('Find parts by specification') plus the discriminating condition ('when no part number is chosen yet'), and enumerates exactly what each of the four categories can be filtered on. An agent can distinguish it from lookup_part (known part number) and search_parts without opening any schema.

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 when-to-use trigger ('no part number is chosen yet, e.g. while designing a circuit or a distribution panel') and routes to the correct follow-up ('Call lookup_part on a part result for prices and listings'). The alternative is named with the condition that selects it.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the remaining burden is light. The description goes further by itemizing what comes back: sale posts, the seller's own wording, purpose, strengths, listed part numbers, and a quote link. It stops short of noting pagination, result caps, or auth, so not a full 5.

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 purpose, then examples, then the return payload, then the routing rule — a sensible order with no filler. It is a dense single block, but each clause carries 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?

With no output schema, the description takes on return-value disclosure and does so adequately (post content, strengths, part numbers, contact link). For a single-parameter read tool with full annotation coverage, nothing an agent needs to invoke it correctly 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 coverage is 100%, so baseline is 3; the description adds real nuance by clarifying the query accepts a product type, an industry, or a maker's line, and works in Korean or English, with multiple examples. That meaningfully extends the terse schema description.

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 and resource: 'Find Korean sellers and makers on BIDON by what they sell.' It explicitly scopes the tool to keyword/industry/line queries, cleanly separating it from lookups keyed on exact part numbers.

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?

States the triggering condition ('when there is no exact part number') and names the alternative with its own condition ('Call lookup_part when a part number is known'). When-to-use and when-not-to-use are both explicit.

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 and non-destructive, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: buyer names are hidden in quotes, quotes are in KRW with lead time, certain vendors (MEAN WELL, MORNSUN, CLAF) are quoted same business day, and results include a summary paragraph plus a purchasable part link.

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 action and resource in the first clause, with returns described after. It is somewhat long and the final sentence about the summary paragraph could be trimmed, but every sentence carries usable information and there is no filler.

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, and the description fully compensates by enumerating what comes back (listings with quantity/price, KRW quotes with lead time, specs, same-spec alternatives, direct-supply status, summary paragraph, part-page link). Nothing needed to invoke or interpret the tool 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?

With a single parameter at 100% schema coverage the baseline is 3, but the description earns extra credit by clarifying that cable names such as 'F-CV 2.5SQ 3C' and 'HFIX 2.5SQ' are valid inputs, broadening the accepted format beyond the manufacturer-part-number example in the schema.

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 ('Look up one electronic or industrial part number') on a named platform (BIDON), and the word 'one' implicitly scopes it against the sibling search_parts. An agent can tell this is a single-part detail lookup rather than a bulk search without opening any schema.

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 description makes the usage context clear (retrieve sale listings, quotes, specs, alternatives for a part) but never states when to prefer this over search_parts, nor any exclusion, and the sibling is not named. Usage is implied by the stated inputs and outputs rather than explicitly routed.

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, and destructiveHint=false, so the safety profile is covered. The description adds matching semantics beyond that: minimum 3 alphanumeric characters, separators ignored, substring containment, plus worked examples. It does not mention result limits or ordering, keeping it short of a 5.

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?

Two sentences, zero filler; the matching rule and its constraints are front-loaded and the routing advice follows. Examples earn their place by showing separator handling.

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-only search tool with no output schema, the description covers input constraints, matching behavior, and the natural next step. Nothing needed to invoke it correctly 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 coverage is 100% (baseline 3), and the description adds real meaning beyond the schema's terse 'Part of a part number': the 3-character minimum, ignored separators, and concrete example values like "LRS-150" and "B0505".

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 (find) and resource (BIDON part pages) with the matching rule (part number contains text), and explicitly contrasts with the sibling lookup_part. An agent can distinguish it from lookup_part without opening either schema.

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 ('Use it when the exact part number is unknown') and names the follow-up tool (lookup_part). The when-to-use and the alternative are both stated outright.

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