Figs, Relationship Expert

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds useful context that answers are 'warm' and 'source-grounded' (implying citations/tone), but says nothing about response length, latency, or scope limits.

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 well-formed sentence with zero filler, and the actor (Figs O'Sullivan) and answer quality are front-loaded. Every clause earns its place by narrowing the tool's domain.

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 one-parameter, read-only, non-destructive tool with no output schema and no side effects, the description covers what it does and what it answers. It omits only secondary details like answer format or grounding sources, which is a minor gap at this complexity.

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 0% schema description coverage, so the description bears the burden. It implicitly characterizes the question as free-form natural-language text on love/conflict/trust/attachment/intimacy/repair, which gives topical framing, but adds no format, length, or phrasing guidance despite a 3-12000 character constraint.

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 (ask) and a specific resource/persona (couples therapist Figs O'Sullivan) plus the topical domain. It is immediately clear what the tool returns, though it does not explicitly differentiate itself from overlapping siblings such as repair_right_now, which also covers the 'repair' topic.

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 by the topic list (love, conflict, trust, attachment, intimacy, repair), so an agent can infer this is for open-ended relationship questions. However, there is no explicit when-to-use vs. when-not guidance and no alternatives named, leaving the agent to guess against five siblings with adjacent purposes.

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 readOnly, idempotent, non-destructive, and closed-world, so safety is fully covered. The description adds essentially nothing behavioral beyond those flags: it doesn't say what the output looks like (single match vs. list), whether there is a cost or signup, or what happens when no match exists for a state/concern combination.

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, front-loaded with the verb and resource, with no filler. Slightly padded by the vague qualifier 'appropriate' and the redundant brand name that already appears in the title.

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 small read-only lookup with no output schema, the definition is minimally viable but underspecified: the agent still cannot tell whether it gets a single recommendation, a list of therapists, or a redirect to another tool, and there is no guidance on what to do with the result.

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 full burden for two parameters. It does map 'state' to US state and 'concern' to relationship concern, which is useful, but it omits the 2-letter abbreviation requirement, the 2000-character free-text nature of concern, and the fact that both parameters are optional.

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 ('Find') and resource ('Empathi therapy or coaching option') plus the inputs that drive selection (state, relationship concern). It is clear what the tool does and roughly how it differs from advice-oriented siblings like ask_relationship_expert, but it never names or contrasts those siblings 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives among the five sibling tools (ask_relationship_expert, get_relationship_assessment, name_the_dance, repair_right_now, wisdom_score_preview). An agent must infer that this is the directory-matching tool rather than an advice tool from the name alone.

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, covering safety. The description adds that it is 'free' and lists topic areas, which is minor added context, but it does not explain what the assessment involves, how it works, or what happens when called.

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 wasted words. It is concise, though the 'Figlet' reference slightly muddies it.

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 tool with one optional parameter and no output schema, the description still omits critical details: the purpose of 'context', what the assessment returns, and how to invoke it meaningfully. Annotations cover safety, but the description is incomplete for 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?

With one optional parameter ('context') at 0% schema description coverage, the description must compensate but mentions nothing about the parameter. The agent has no idea what 'context' should contain or how it affects the assessment.

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 ('Get the ... assessment'), but the brand mismatch between 'Figlet' in the description and 'Empathi' in the title creates confusion. It also fails to distinguish this tool from siblings like ask_relationship_expert or wisdom_score_preview, leaving the agent unsure of its unique scope.

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 alternatives, no prerequisites, and no indication of what situation calls for an assessment. The description merely says it retrieves an assessment, leaving the agent to infer usage.

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 the full safety profile (readOnly, non-destructive, idempotent, closed-world), so the bar is lower. The description usefully discloses what comes back (named pattern, protections, fears, repair sentences), which is behavioral context beyond the annotations, but it omits how the input is processed or any limits.

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 names the action first and then enumerates the outputs. No filler; every clause earns its place. Slightly dense but well structured.

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 does the work of explaining return values (pattern name, protections/fears, one repair sentence each), and annotations cover safety. The main gap is the undocumented input parameter and no usage routing, but overall it is close to complete for a one-param 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?

The single parameter (what_happened) has 0% schema description coverage, so the description must carry meaning. It says to describe a recent conflict with your partner, which maps the param to intent, but adds no format, scope, or length guidance (e.g., the 12,000-char cap) beyond that.

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+resource: it takes a described conflict and returns a named repeating pattern, what each partner is protecting/fearing, and repair sentences. This is clear and concrete, including a sample output ("the Waltz of Pain"). It does not explicitly differentiate itself from siblings like repair_right_now or ask_relationship_expert, 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?

Usage is implied by "Describe a recent conflict with your partner," which signals when the tool applies. However, there is no explicit when-not guidance and no named alternative among the five siblings (ask_relationship_expert, repair_right_now, etc.), leaving routing 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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral value by disclosing the shape of the response (a staged, ordered three-step sequence) that no output schema provides; it says nothing about length, tone, or personalization.

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, front-loaded with the deliverable and its three ordered steps. No filler, no restatement of the title, and the sequence order is preserved in the phrasing.

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 tool with no output schema the description adequately conveys the return shape, and annotations cover safety. The gap is input guidance: the required 'situation' field and optional 'my_part' are undocumented everywhere, which matters for a tool whose output quality depends entirely on the supplied narrative.

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% for two parameters, one required, so the schema gives no field-level documentation. The description never mentions 'situation' or 'my_part' — what to include, how much detail, or when the optional 'my_part' matters — so an agent must guess at input content quality.

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 concrete deliverable (a three-step repair) and enumerates the three steps, so an agent knows exactly what calling it produces. It does not compare itself to siblings like ask_relationship_expert or name_the_dance, so the 'right now / acute conflict' niche must be inferred from the name and title.

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 rather than stated: 'right now' plus the title 'Help me repair after a fight' signals immediate post-conflict de-escalation. There is no explicit when-not guidance or named alternative for slower, reflective, or expert-advice needs, leaving routing to the agent's 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, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that the output is 'non-numeric' and a 'quick read', which is useful context about the result shape, but it does not explain whether the insight is generated by a model, cached, or how it differs from the full assessment.

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 single sentence is compact and front-loaded with the input request. However, it wastes its only sentence on input specification and never states what the tool actually does, which is a structural misplacement of 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?

With no output schema and a sparse one-parameter schema, the description should carry the burden of explaining what the agent gets back and when to use it. It does neither, leaving the agent unable to distinguish this from the three other relationship-assessment 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?

There is exactly one parameter, 'responses', with 0% schema description coverage and no enum. The description indicates the expected content (a recent fight, partner's feelings, an alternative action), which is useful, but it does not tell the agent the format needed for the string or the minimum length (3 chars) or maximum (12000 chars). The single-param baseline would be 4, but the description leaves the format requirements ambiguous.

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 describes what input to provide rather than what the tool does or returns. 'One non-numeric Wisdom Score insight' is abstract and undefined — it does not state the resource being acted on (e.g., 'analyze a relationship incident and return coaching insight') nor distinguish it from siblings like get_relationship_assessment or ask_relationship_expert.

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 when-to-use guidance. The description never mentions the sibling tools or explains why an agent would pick this over get_relationship_assessment or ask_relationship_expert. One sibling, find_couples_therapist, is clearly a different intent, but the three assessment/expert tools are not differentiated at all.

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