Agent Access Door Check

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

With no annotations, the description carries the full behavioral burden. It usefully discloses that no verdict is returned and that the evidence must be validated, but it omits side effects, permissions, idempotency, and what 'fresh assembly' actually does.

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 front-loaded sentence with no filler; the return caveat is parenthetically placed to avoid disrupting the main action. It is appropriately sized.

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 tool with three required parameters (including a nested evidence object), no annotations, and no output schema, the description is too thin. It handles output expectations partially via 'no verdict returned' but leaves parameter meaning and invocation context insufficiently documented.

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 0%, so the description must explain the three required parameters, but only 'evidence' is indirectly addressed as a 'validated evidence doc.' The roles of 'site' and 'task' are left completely opaque.

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 specific verb ('Submit') and resource ('validated evidence doc') and states the downstream action ('fresh assembly') plus a return caveat. It does not differentiate from sibling tools such as collateral_report or get_receipt, but the evidence-assembly focus is clear enough on its own.

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 when-to-use or when-not-to-use guidance is given, and no alternative tool is named. 'Validated evidence doc' implies a precondition, but the description never tells the agent when this submission is appropriate versus other 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?

No annotations are provided, so the description carries the full burden. It implies a read-only report ('report', 'site-facing') but does not disclose permissions, side effects, rate limits, or whether any state is modified.

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?

It is a single sentence fragment, so it is short, but the brevity reflects under-specification rather than efficient communication; key information is missing.

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 annotations, no output schema, and 0% parameter documentation, the description is far too sparse for an agent to invoke the tool correctly. It never states what the report contains, how to supply 'task', or what a COLLATERAL-BLOCKED verdict means in this context.

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 0% and the description does not explain either required parameter ('site', 'task'). 'Site-facing' hints at the site parameter but does not define it, and 'task' is entirely unaddressed.

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 identifies the resource as a 'collateral report' and adds a condition ('COLLATERAL-BLOCKED verdict') and audience ('site-facing'), but it uses a noun phrase with no action verb (generate? fetch?). It does not differentiate from siblings like assemble_evidence or get_receipt.

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 phrase 'for a COLLATERAL-BLOCKED verdict' implies the tool is used in that verdict context, giving a minimal use condition. However, there is no explicit when-to-use versus alternatives, no exclusions, and no guidance on prerequisites.

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 burden and does disclose meaningful operational behavior: cost ($0.05/call), the x402 payment mechanism via X-PAYMENT header, a one-time free call per operator, and plan quotas for cached vs. fresh calls. It also hints at output content ('evidence + route'). It stops short of stating read-only semantics, latency, or failure 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?

One dense sentence that front-loads purpose (access verdict) before commercial details, with zero filler sentences. It is jargon-heavy and run-on, but every clause conveys something actionable and 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?

For a tool with no output schema, no annotations, and a nested-object parameter at 0% schema coverage, the description does useful work by enumerating verdict values and advertising 'evidence + route' output plus pricing. It still omits the meaning of today/evidence/is_partner and any detail on the shape of the returned evidence, leaving real gaps.

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% across five parameters, so the description must compensate. 'per-site x per-task' loosely maps to the site and task parameters and 'PARTNER-ONLY' hints at is_partner, but today, evidence (a nested object), and the precise semantics of the others are entirely unexplained in both schema and 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?

The description states a specific function: returning a per-site x per-task access verdict, and enumerates the six possible verdicts (PERMITTED, LICENSED-ONLY, PARTNER-ONLY, POLICY-BLOCKED, COLLATERAL-BLOCKED, UNKNOWN). That is far more concrete than the opaque name 'door_check'. It does not, however, differentiate itself from siblings like assemble_evidence or collateral_report, even though it references producing 'evidence'.

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 word 'Pre-flight' implies the tool is called before attempting access, which is useful contextual guidance. Beyond that there is no explicit when-to-use vs. when-not, and no sibling alternative is named, so the routing decision is left largely to inference.

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 it does not disclose what happens when the receipt_id is unknown, whether any auth/scope is required, or whether results are cached/immutable. 'Stored' hints at persistence but nothing more.

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 tight sentence with the resource front-loaded after the verb. No waste, though it is almost too terse for a tool whose domain term 'verdict receipt' is unexplained.

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 no output schema and no annotations, the description is workable but thin: it never clarifies what a 'verdict receipt' contains or how it differs from sibling outputs. Adequate minimum, not more.

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 0%, but there is only one required string parameter and the description's 'by id' maps directly onto receipt_id, conveying the lookup semantics. It adds no format, source, or example detail beyond the obvious, so it is only minimally compensating for the schema gap.

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 ('Fetch') and resource ('stored verdict receipt') with the lookup key ('by id'), so the agent knows this is a retrieval-by-identifier operation. It does not contrast itself against siblings genesis_pin or verify_candidate, so it stops 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?

No guidance on when to use this versus verify_candidate or genesis_pin, and no prerequisites or exclusions stated. The agent must infer the retrieval context entirely.

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?

No annotations are provided, so the description carries the full behavioral burden. It mentions an alert on "class change," but omits persistence, permissions, watch lifetime, alert delivery, and what "class" means.

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 front-loaded sentence with no filler. Its extreme brevity is under-specification rather than efficient conciseness for a tool with two required parameters and no annotations.

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 annotations, no output schema, and 0% schema description coverage, the description leaves the agent without enough information to invoke the tool correctly. Key details such as alert channel, watch duration, and the meaning of "class change" are absent.

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 for both parameters. It names "site" and "task" and hints at an "x" relation, but adds no format, meaning, or expected values for either.

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?

"Watch" is a specific verb and "site x task" names the resource pair, so the description is not a pure tautology. However, "class change" is undefined and no sibling relationship is established, leaving the actual purpose vague.

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 when-to-use guidance, no when-not-to-use guidance, and no alternatives among the sibling tools. An agent has no routing information beyond the bare name.

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