Figs, Relationship Expert

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds useful context about tone ('warm') and sourcing ('source-grounded'), but it does not describe the answer format, citation behavior, or any limitations. This is meaningful but not extensive additional disclosure.

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 compact, front-loaded sentence states the action, the expert, the answer quality, and the topic domains. Every element earns its place; there is no filler or redundancy.

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 simple read-only Q&A tool with one parameter and existing annotations, the description is largely sufficient: the agent knows what to ask, who is being asked, and what kind of answer to expect. A minor gap is the absence of explicit details about the output structure or how sources are presented, but that does not critically impede correct invocation.

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 100%, and the single 'question' parameter is adequately described in the schema. The tool description adds topic context but does not add new parameter-level semantics such as format requirements or constraints, so baseline 3 is appropriate.

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 ('Ask') plus a named resource ('couples therapist Figs O'Sullivan') and clearly defines the topical scope: love, conflict, trust, attachment, intimacy, or repair. This also distinguishes it from sibling tools like find_couples_therapist or get_relationship_assessment.

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 intended use is implied by the question-and-answer framing and the topic list, but the description does not explicitly state when to use this tool instead of a sibling like get_relationship_assessment or repair_right_now, nor does it give exclusion 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 cover read-only, idempotent, and non-destructive behavior. The description adds that the tool selects or recommends an option based on inputs, which is useful, but it does not disclose return shape, error behavior, or what happens with unsupported or missing inputs. No contradiction with 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 a single well-structured sentence, front-loaded with the verb and resource, with no redundant or wasted words. It is concise and easy to parse.

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 simple two-parameter read-only tool, this is mostly adequate, but with no output schema the description should say a little more about what the returned 'option' looks like. The mismatch between the description implying both state and concern are needed and the schema listing zero required parameters is also left unaddressed.

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 input schema already documents both parameters (state and concern) with 100% coverage and includes validation constraints. The description only restates 'state and relationship concern' and adds no new format, default, or dependency semantics beyond the 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?

The description names a specific action ('Find') and a concrete resource ('Empathi therapy or coaching option'), with clear selection inputs (US state, relationship concern). This distinguishes it from sibling tools like ask_relationship_expert or get_relationship_assessment, even without naming them 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?

The description implies the right context: use it when the user needs an Empathi therapy/coaching match and provides a state and concern. However, it gives no explicit when-not-to-use guidance and does not reference alternative sibling tools, so the agent must infer the boundary.

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 annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds content-level transparency by naming the relational domains explored, but it does not disclose how the optional context parameter affects the assessment or what the returned assessment 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?

The description is a single, reasonably efficient sentence that front-loads the action and resource. It includes some low-value wording ('free', the unexplained 'Figlet') but overall it stays compact and readable.

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?

This is a simple read-only tool with one optional parameter and annotations covering safety, so the description does not need to carry much. However, it never explains what the returned assessment contains, how the context parameter is used, or why an agent should select this over related sibling tools.

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 100%, and the sole parameter 'context' already has a clear description in the schema. The tool description adds no further semantic detail about the parameter, matching the baseline for full 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 clearly uses a specific verb ('Get') and resource ('the free Figlet assessment'), and lists the topics it covers: relationship patterns, attachment, communication, conflict, and relational strengths. However, it does not explicitly distinguish this from sibling tools like wisdom_score_preview, and the unexplained 'Figlet' term adds ambiguity.

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 about when to choose this tool over alternatives such as ask_relationship_expert or wisdom_score_preview. The title and description imply it is for taking an assessment, but no explicit when-to-use or when-not-to-use context is provided.

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 safety profile is covered. The description adds useful context about what the tool will produce, but it discloses no further behavioral traits such as hidden dependencies, limitations, or response handling.

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 well-formed sentence that moves from the required input to the expected output with no filler. Every phrase earns its place, and the core instruction is front-loaded.

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, one-parameter naming tool, the description covers the input, the purpose, and the return contents even though no output schema is present. It is slightly incomplete only in not addressing when to prefer sibling tools or how much conflict detail is needed.

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 carries the burden of explaining the sole parameter, what_happened. 'Describe a recent conflict' directly maps to the parameter and gives meaningful semantic guidance. It does not specify format or level of detail, but for a single free-text input this is sufficient.

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 action ('will name') and a specific scope ('a recent conflict'), and it enumerates the concrete outputs: the Waltz of Pain, each protector and fear, and a sentence per partner. It does not explicitly differentiate from sibling tools, but the output is distinctive enough that an agent can infer what this tool does.

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 opening instruction 'Describe a recent conflict' implies when this tool is appropriate, and the output framing suggests a naming/reflection use case. However, it does not provide exclusions or direct comparison with siblings like ask_relationship_expert or repair_right_now, so the guidance is implied rather than explicit.

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 and idempotentHint=true, so the safety profile is covered. The description adds that the tool returns a structured three-step process rather than open-ended advice, which is useful behavioral context. No contradiction with 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?

A single, dense sentence that front-loads the purpose and then enumerates the three steps. Every clause earns its place; no filler. Ideal for quick reading.

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 has only two parameters and no output schema, but the description omits any semantics for the inputs, especially 'my_part', which could be unclear. While the tool is simple and domain cues make 'situation' inferable, the agent is not fully equipped to construct a correct invocation without more explicit guidance.

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%, and the description does not explain what 'situation' or 'my_part' should contain. The names are suggestive but the description adds no parameter-level meaning, leaving the agent to guess at the expected input format. This earns a low score.

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 concrete outcome: 'Get a three-step repair for right now' and enumerates the three steps. This differentiates it from sibling tools like get_relationship_assessment or find_couples_therapist, which target deeper or longer-term relationship help. However, it does not explicitly name a sibling or contrast itself, so it falls just 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 phrase 'for right now' signals this is the immediate-repair tool, providing clear context for post-fight use. No exclusions or comparison to sibling tools are given, so the agent must infer when deeper assessment or expert help is more appropriate. This matches 'clear context, no exclusions'.

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 safety profile is covered. The description adds that the result is a single non-numeric insight, which is useful but does not go deeply into behavior beyond that.

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 that front-loads the input requirements and the output type. Every part contributes to understanding how to use the tool, with no filler or redundancy.

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 simple one-parameter, read-only tool without an output schema, the description is largely complete: it explains the expected input and the nature of the output. It could add more context about what a 'Wisdom Score insight' is or how to route between sibling tools, but those are not critical 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?

Even though schema description coverage is 0%, the description compensates fully for the single 'responses' parameter by specifying exactly what the user should share: a recent fight, what the partner may have felt, and what could be done differently. This adds clear meaning beyond the raw 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?

The description clearly states what the tool does: it takes a recent fight, the partner's likely feelings, and an alternative action, and returns one non-numeric Wisdom Score insight. This is a specific action and resource, though it does not explicitly differentiate the tool from sibling relationship 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 implies usage context: use this when you have a recent fight and want a 'quick read' or preview insight rather than a full assessment. However, it does not explicitly say when to choose this tool over alternatives like get_relationship_assessment or ask_relationship_expert.

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