GateCore Marketplace

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

Beyond the annotations, the description discloses that authorization is not direct: purpose is forwarded and the gateway policy decides whether access is allowed. This is a valuable behavioral nuance, and there is no contradiction with the destructiveHint annotation, though the description does not elaborate on side effects.

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 description is two concise sentences with no redundancy. The primary verb-resource statement is front-loaded, and the second sentence adds the policy nuance without extra 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?

The main authorization flow is described, including the purpose forwarding and gateway policy, but the description omits return values, error semantics, and any meaning for max_price_cents. With no output schema, an agent must still infer several important runtime details.

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 0%, so the description must compensate, but it only clarifies the purpose parameter's forwarding behavior. The required listing_id and max_price_cents parameters receive no additional meaning, leaving the agent to infer their semantics from names alone.

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 clearly names the verb and resource: 'Authorize signed access to a governed listing.' It specifies the purpose-forwarding behavior, but it does not explicitly differentiate from the sibling tool complete_access, so it falls short of a 5.

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 implies usage by stating what the tool does and explaining the gateway decision, but it gives no explicit when-to-use or when-not-to-use guidance and does not contrast with alternatives like complete_access or procure.

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?

The description adds meaningful behavioral context beyond the annotations: seller output is hashed locally and explicitly never forwarded or returned, and the tool returns a terminal signed receipt. It complements the destructiveHint=true annotation without contradicting it.

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, every phrase earned: 'hash', 'locally', 'attest completion with the buyer agent key', 'terminal signed receipt', and the crucial 'never forwarded or returned'. No padding.

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?

Moderate completeness: the description covers the primary safety property (no output leak) and the terminal receipt, but leaves gaps around what must be in the ticket, what the outcome string should contain, and prerequisites. With three required params and a nested object, a bit more context would strengthen correct usage.

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 0% schema description coverage, the description must carry the burden. It explains seller_output well and hints at ticket (buyer agent key) and outcome (completion), but leaves exact meaning and valid values for ticket and outcome to inference.

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 clear action: hash seller output, attest completion, and return a terminal signed receipt. It conveys the resource and outcome, but does not explicitly differentiate itself from siblings like authorize_access or procure, so it earns a 4 rather than a 5.

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?

Usage is implied: this is the final step after seller output is available, where the buyer agent key is used to attest. However, there is no explicit 'use when X, avoid when Y' guidance or mention of sibling alternatives to route the agent to the correct tool.

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 that the tool is read-only, idempotent, and non-destructive, and the description does not contradict them. The description adds useful behavioral detail: the results are governed marketplace capabilities containing machine-readable pricing, scopes, and trust terms, and the ordering preserves the marketplace's organic order. It does not cover pagination or result limits, but those are not required given the strong annotation coverage.

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 description is two sentences and contains no filler or redundancies. The core purpose is front-loaded, with the ordering guarantee in the second sentence adding meaningful behavioral information without extra length.

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 read-only discovery tool with four optional parameters and no output schema, the description gives a useful high-level picture: listing-like results with pricing/scope/trust details and original ordering. However, it leaves out parameter semantics and sibling-tool distinctions, so the agent has enough to start but not enough to select filters confidently.

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 0%, so the description needs to compensate, but it barely does. 'minimum trust terms' and 'machine-readable pricing' hint at trust and price-related parameters, but tags, query, min_trust, and max_price_cents are not explained, including units, filtering behavior, or combinations. An agent would have to infer semantics from parameter names.

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 uses a clear verb ('Discover') and identifies the resource: governed GateCore marketplace capabilities, including machine-readable pricing, required scopes, and minimum trust terms. It conveys the type of data returned, though 'capabilities' is slightly abstract and it does not explicitly differentiate from sibling listing tools.

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 gives no explicit guidance on when to use discover_listings versus get_listing, list_procurements, or other siblings. Usage is only implied by the tool's name and general discovery wording, with no stated exclusions or alternative-selection criteria.

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 description does not need much safety reporting. The description adds useful context by stating the listing is 'governed' and that terms are machine-enforceable, but it does not disclose any error or authorization edge cases. It is adequate but not rich.

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 entire description is one focused sentence that starts with the verb and resource, and then lists the specific terms it returns with a colon — no wasted words. It is structured well for quick agent scanning, missing all necessary.

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 tool is simple (one parameter, no output schema), and the description fills the most critical gap by naming exactly which fields appear in the returned terms. It doesn't mention the success/failure envelope or a fallback like what to do if the listing does not exist, but with the overall built-in readOnly hint and the tool's simplicity, the description is complete enough for a correct call.

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 schema contains only listing_id with no description for it, leaving 0% schema description coverage. The description's 'Fetch one listing' is some compensation — it implies listing_id identifies the target — but it never actually explains the parameter or the expected value format. The tool name makes the self-evident, but the description itself adds minimal direct param meaning.

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 the exact resource (a governed marketplace listing) and carries a precise verb ('Fetch'), also limiting it to 'one' listing, which distinguishes it from discover_listings and other collection-based siblings. The enumeration of what it returns adds valuable specificity.

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 implies that this tool is correct when a specific listing is in-hand, since it fetches a single listing and its contract terms. However, it does not explicitly name alternatives or exclude cases such as searching/ discovering listings, so the usage context is inferred rather than 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds 'credential tenant' scoping and 'public modes' context but does not disclose return shape, ordering, pagination, or whether the result is a full list.

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?

One sentence, no filler. The action and resource are front-loaded, and the additional context is concise.

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-parameter, read-only list operation with strong annotations, the description is nearly complete. It could be slightly clearer about what 'public modes' means and what the return contains, but the tool's core callable behavior is evident.

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?

There are zero parameters and schema coverage is 100%, so the description does not need to explain parameter meaning. This is a no-parameter tool, making parameter semantics a non-issue.

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 ('List') and resource ('procurement decisions') and adds useful scope ('credential tenant', 'public modes'). This clearly distinguishes it from sibling tools like procure or get_listing, which are action- or listing-oriented.

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?

No explicit when-to-use guidance, exclusions, or alternatives are mentioned. The description implies this is a read-only list operation, but it never explains when the agent should choose this tool over siblings such as discover_listings or procure.

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?

The description does not contradict the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false). It adds useful behavioral context by stating that the result is a PROCURE, REVIEW, or DENY decision and that gateway delegation happens 'when eligible'. However, it does not disclose the side effects of that delegation or whether the action creates or modifies a persisted record, which would add more beyond the annotations.

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 description is short and front-loaded, but the second sentence is dense with undefined domain terms ('GateCore's baseline', 'full mode', 'gateway delegation'). It is not overly verbose, but the compromised clarity for brevity.

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 destructive, 7-parameter tool with no output schema and sibling tools in the same domain, this description is not complete. It fails to define what 'governed procurement' means, what inputs drive the PROCURE/REVIEW/DENY outcome, how delegation is triggered, and what the relayed response looks like. An agent would need to guess at invocation semantics.

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 schema description coverage is 0%, and the description does not explain any of the seven parameters. The mention that 'identity comes from the MCP access key and trust from GateCore's baseline' muddies the role of the required requester_agent_id and requester_trust fields. This is a critical gap, as the description adds no meaning or format to the parameter names.

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 opens with a specific verb and resource ('Request governed procurement for a listing') and even names the decision outcomes (PROCURE, REVIEW, DENY), which helps an agent infer the tool's function. However, it never differentiates this from the sibling request_listing_access or authorize_access, so the distinction between 'procurement' and 'access' is left to the reader.

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?

No explicit guidance is provided about when to use this tool versus the alternatives. The phrase 'In public full mode' hints at a conditional, but the description never says what mode the agent is in, when that mode applies, or how the tool's behavior changes. There is no wean to choose between procure and the sibling tools.

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 provide idempotentHint=true and destructiveHint=false. The description repeats 'idempotent' but adds the context that the request targets the credential's tenant and agent. This is mild additional context but not a rich behavioral disclosure (e.g., side effects, required permissions, or return format).

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?

A single, front-loaded sentence that is efficient and contains no filler. Every word adds meaning.

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 is extremely brief for a mutation tool. It doesn't explain what a listing-access request entails, what happens after submission, or any prerequisites. With no output schema and minimal annotations, the agent has little context to call it correctly.

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 0%, so the description must compensate. It only hints at 'tenant and agent' but does not explain the parameters (agent_id, listing_id) or their roles. The agent_id is optional and defaulted to null, but no meaning is given. This is insufficient given zero schema coverage.

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 ('Submit') and a clear resource ('listing-access request'), and it adds the scope 'for the credential's tenant and agent.' This is clear and specific, but it does not explicitly differentiate from siblings like authorize_access or complete_access, so it misses the top score.

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?

There is no guidance on when to use this tool versus the alternatives (e.g., authorize_access, complete_access). No conditions, prerequisites, or exclusions are mentioned. The agent must infer when this is appropriate.

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 provide no useful hints—all flags are false, so the description must disclose behavior. While it mentions 'consented' (a requirement), it does not explain whether the operation is a write, what happens on success or failure, if it is idempotent, or any authentication requirements. The agent is left with minimal understanding of side effects, making this insufficient for a mutative action.

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 description is a single concise sentence with no fluff, front-loading the core action. It is appropriately compact for a short tool, but the brevity means it omits key details. For the conciseness dimension itself, it scores well, though it could be slightly more informative without becoming verbose.

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, sparse annotations, and an input schema lacking descriptions, the description is the only resource for an agent. It only states the high-level action and leaves critical details—such as lead structure, listing requirements, error handling, and return value—completely unexplained. This is inadequate for a tool with complex input.

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 0%, so the description must compensate, but it does not. It never references the parameters 'listing_id' or 'lead', nor does it explain their structure or meaning. The 'lead' object is an arbitrary object with additionalProperties, yet the description offers no guidance on required fields or format. This is a severe gap given the flexible input.

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 clearly states a specific verb ('Submit') and resource ('a consented consumer lead') targeted at 'a supported published listing'. It distinguishes the action from siblings by focusing on lead submission, though it does not explicitly mention alternatives. The phrase 'supported published listing' is somewhat vague, so it does not fully differentiate from related tools.

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 provides no guidance on when to use this tool versus alternatives like 'procure' or other siblings. There are no scenarios, exclusions, or conditions that help an agent decide between this and similar tools. Usage context is implicitly the action of submitting a lead, but no explicit direction is given.

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