Human as a Service (Geoff)

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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds meaningful behavior beyond that: the call is asynchronous, returns an id and URL to poll, and an optional callbackUrl receives the answer. It doesn't state latency, whether questions can be withdrawn, or what the callback payload looks like.

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 tight sentences, front-loaded with the action and return behavior, then scope. The domain list is slightly long but earns its place by defining the expert's remit; no filler sentences.

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 async, no-output-schema tool, the description covers the essentials: what happens on call, how to retrieve the answer, and the domain limits. It leaves the callback payload contract and the interaction with the get_answer sibling unstated, which is a minor gap.

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 low (17%) across 6 params, so the description should compensate more than it does. It does explain callbackUrl's effect (receives the answer) and the polling model, and 'person' is documented in-schema, but tags, asker and context are left entirely to the schema with no added 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?

States a specific verb and resource ('Leave a question for a person') and describes the async result (id + URL to poll), which implicitly contrasts with the get_answer sibling. It does not explicitly name get_answer or list_people as alternatives, so it stops 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?

The description gives scope guidance for the target expert ('emotions, sensations, intuition... product strategy, Kubernetes') and an explicit exclusion ('Not legal, medical or financial advice'), which helps decide when to use it. However, it never states when to use ask_person versus get_answer or list_people, nor any prerequisite for asking.

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 safety is covered. The description adds genuinely new behavioral context: the word 'poll' signals an asynchronous, possibly repeat-until-ready operation and that a question has a status separate from an answer, which annotations do not convey.

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 zero waste, front-loading the action ('Poll a question by id') before the returned data.

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 must carry return-value burden, and it does name the two things returned (status and answer). It stops short of explaining what statuses exist or that the answer may be absent while pending, which would fully close the loop for a polling tool.

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 is one parameter with 100% schema description coverage, and the schema already explains the id is 'returned by ask_person'. The description's 'by id' adds no syntax or format detail beyond that, 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?

The description gives a specific verb and resource ('Poll a question by id') plus the payload it retrieves ('its status and answer'). It is clearly distinct from ask_person (which creates the question), though it never names the sibling 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?

Usage is only implied: 'Poll ... by id' combined with the schema note that the id comes from ask_person tells the agent this follows an ask_person call, but the description itself states no when/when-not or alternative. Adequate but leaves sequencing 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?

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds content-level context about what the listed entries contain (expertise, will/won't answer, SLA, price), which is genuinely useful, but says nothing about pagination, filtering, or result 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 tight fragment with no filler, and the key information ('who can be asked') is front-loaded. It reads as a data gloss rather than a sentence, which slightly weakens it as a standalone purpose statement.

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 must characterize the return values, and it does so by naming the four field types each person entry carries. For a zero-param listing tool this is close to sufficient, though it omits any statement about the number of results or ordering.

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, so there is nothing for the description to disambiguate beyond what the empty schema already shows. Baseline 4 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?

The title supplies the verb+resource ('List the people'), and the description enumerates the specific fields returned (expertise, SLA, price), so the resource is concrete. It is distinguishable from ask_person/get_answer by implication (discovery vs. interrogation), but the description itself never states a verb or explicitly contrasts with the 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?

The phrase 'Who can be asked' hints at a discovery step preceding ask_person, but there is no explicit when-to-use statement, no condition selecting it over ask_person or get_answer, and no exclusions. Guidance is left entirely to inference.

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