Agent Procurement Manager (APM)

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

With no annotations, the description carries the full burden and does disclose the key behavioral facts: it is free, never executes a purchase, and has no payment side effect. It also surfaces the auth/payment model (USDC on Base, eip155:8453, x402) for the execution path. Missing only pagination/refresh behavior.

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 sentence is well front-loaded, but 'Free.' immediately followed by 'This tool is free and never executes a purchase' is redundant, and the final sentence describes apm_quote's execution flow rather than this tool's behavior. Some trimming would tighten it.

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 zero-param listing tool with no output schema, the description tells the agent what it returns (categories plus registered/active supplier counts) and what the natural next step is. Only the exact response shape is left unspecified, which is a minor gap given no output schema exists.

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?

The tool takes zero parameters and the description introduces no phantom inputs, so the baseline of 4 applies. No parameter meaning is needed or claimed.

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 (List) and resource (APM's phase-1 procurement categories), enumerates the exact categories returned, and specifies the payload (verified supplier counts). It also names apm_quote, so the agent can separate it from its siblings 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?

Clearly frames this as the free discovery step and explains the downstream path (take quote_id from apm_quote, then POST /task and pay via x402). It stops short of an explicit when-not-to-use statement, but the role relative to the siblings is easy to infer.

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?

With no annotations, the description carries the full behavioral burden and does disclose the key traits: it returns a ranked candidate set, it executes nothing and charges nothing, and it is non-destructive. It stops short of covering any rate limits or auth requirements, but for a read-only preview the essential safety profile is well communicated.

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-loads the core purpose and the non-execution guarantee before pivoting to the execution path, with every sentence carrying useful information. It is somewhat dense and the execution-path sentence is long, but nothing is redundant.

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 appropriately explains return contents (candidate set, score breakdown, latency, success rate, selected supplier, price). Combined with the routing instructions, an agent has enough to invoke it correctly; only per-parameter detail is absent, and the schema largely covers that.

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 75%, so most parameters (task, input, category, max_budget) are already documented. The description adds no per-parameter meaning beyond what the schema provides, so it neither compensates for the small coverage gap nor extends definitional value; the 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 and resource ('returns the top-3 candidate suppliers APM would consider') and enumerates the exact payload (names, unit prices, score breakdown, latency, success rate, selected supplier, customer price). It implicitly contrasts itself with apm_quote by framing itself as a no-cost preview, so an agent can distinguish it from siblings.

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 when-to-use ('free sample' preview) and when-not ('executes nothing and charges nothing'), plus the exact alternative path: get the quote_id from apm_quote, then POST /task and pay customer_price in USDC on Base. The routing to the right sibling and endpoint is spelled out.

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?

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses the scoring weights, that the tool is free, that it never purchases, and the exact payment mechanism (USDC on Base eip155:8453 via x402). An agent knows the cost, side effects, and next step without external 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?

Dense but front-loaded: purpose first, then return values, then the execution path. Every sentence carries information, though the scoring-weight parenthetical and payment details make it slightly heavy for a single paragraph.

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 and no annotations, the description explicitly enumerates the return values (quote_id, chosen supplier, scored candidates, customer_price) and the full two-step flow. Nothing needed to invoke or sequence 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 75%, so structured fields already document most parameters. The description adds no meaning for input, category, or max_budget beyond noting the task gets classified, so the 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 and resource ('Get a free Agent Procurement Manager quote') and richly details the process: task classification, supplier scoring, and pricing. It is completely distinguishable from apm_categories and apm_preview by function, though it never explicitly names those siblings, so it falls just short of full sibling differentiation.

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 frames when to use it ('free and never executes a purchase') and when to move on, giving the exact execution path ('take the quote_id ... then call POST /task?quote=<quote_id>'). The when-to-use versus when-to-execute boundary is unambiguous.

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