HUMAN API

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

No annotations are provided, so the description carries the full behavioral disclosure burden. It adds the useful detail that humans are 'voluntary,' but it does not clarify whether this is a read-only discovery/search operation, whether it contacts or assigns humans, what permissions or privacy constraints apply, or what the result represents.

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 the verb first and no redundant filler. Its brevity is appropriate, even though it leaves other gaps to be filled elsewhere.

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?

Given no annotations, no output schema, and zero schema description coverage for both parameters, the description is too thin. It does not explain return values, parameter usage, filtering behavior, or how discovery relates to the sibling tools that would likely follow it.

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 should compensate for the two undocumented parameters. It indirectly lists capability categories that may relate to the 'capability' field, but it never mentions the 'location' parameter or explains how either filter should be used.

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 ('Discover voluntary humans') and scopes it to physical-world tasks requiring human presence, perception, or judgment. It is clear what the tool does, but it does not explicitly distinguish itself from siblings such as request_human_help or get_task_status.

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 clear usage context: use it for physical-world tasks requiring presence, eyes, hands, inspection, photography, local access, verification, perception, or human judgment. It does not provide exclusions or explicitly name alternatives, so it falls short of full when/when-not guidance.

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 must carry the full behavioral burden. It implies a read operation, but does not state whether it is side-effect free, what happens if the task is still pending, or how errors are reported.

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 with no wasted words. It is perhaps too sparse for its purpose, but structurally efficient.

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 tool with no annotations, no output schema, and an undocumented parameter, the description is too thin. It does not explain return shape, pending-state behavior, or error conditions.

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 single required 'id' parameter has 0% schema description coverage, and the description adds no meaning about what the id identifies or its expected format. With one undocumented parameter, the description should compensate but does not.

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 ('Retrieve') and resource ('current human decision and status for a HUMAN API task'). It is reasonably distinguishable from discover_humans and request_human_help, though it does not explicitly name or contrast with those 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?

There is no guidance on when to call this tool versus alternatives, nor any stated prerequisite such as needing a task created via request_human_help. The intended polling/status-check usage is only 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?

With no annotations, the description carries the full behavioral load. It does disclose the key non-obvious trait that humans participate voluntarily and can decline ('Human acceptance is mandatory'), which is genuinely useful. But it says nothing about async/blocking behavior, what identifier or status is returned, timelines, or what happens to budget on decline.

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 short sentences, zero padding, with the core purpose front-loaded and the triggering examples second. The most surprising constraint (voluntary acceptance) lands last with emphasis.

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?

Seven parameters, no annotations, no output schema, and 14% schema coverage — yet the description addresses none of the budget, deadline, or location semantics and does not say what a call produces. For a tool this configurable, the definition leaves the agent under-informed about how to fill most fields.

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?

Only 1 of 7 parameters (task) has schema description coverage at 14%. The description never mentions deadline, location, requirements, budget_amount/budget_currency, or discovery_source, so nothing compensates for the coverage gap on a mostly undocumented 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?

States a specific verb and resource: requesting voluntary human execution of a real-world task an AI cannot perform digitally. That clearly separates it from discover_humans (find humans) and get_task_status (poll), even though the siblings are never named explicitly.

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 a concrete, well-targeted list of triggering situations: physical presence, inspection, photos, reading labels, local access, verification, human judgment. It lacks an explicit when-not clause or a pointer to the sibling tools, which is what keeps it off a 5.

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