Ariadne for Therapists

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

Annotations already cover read-only/idempotent/open-world safety, so the bar is lower, yet the description adds substantial non-structured behavior: the tool is free, capped at 3 distinct practices per caller per week, and repeat audits of the same practice return the saved report rather than re-running. Those are exactly the operational facts an agent needs before invoking.

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 sentences, front-loaded: capability and return value first, then when-to-use, then cost and rate-limit constraints. No sentence is filler.

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 carries the return contract (0-100 score plus prioritized, therapist-appropriate fixes) and also discloses cost and per-caller quota behavior. Nothing an agent needs to call this correctly or set user expectations is missing.

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%, so the baseline is 3. The description notes the website input is optional and that supplying it extends the check, but that merely restates the schema's own parameter description without adding format or edge-case guidance.

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 (checks) and specific resources (Google Business Profile, optional website) plus the concrete output (a 0-100 setup score with prioritized fixes). An agent can distinguish this from get_ariadne_overview and write_sample_google_post immediately, since neither audits a practice's local-search presence.

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 explicit trigger conditions: a therapist asking how findable their practice is, why they aren't showing up on Google, or what to fix first. It stops short of naming the sibling tools as alternatives or stating when not to use it, so it is clear context without full routing.

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, non-destructive, and closed-world, so the safety profile is fully covered. The description adds the content scope (audience fit, pricing, ethics), but nothing about freshness, rate limits, or behavior on repeated calls. Adequate but not rich beyond structured data.

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?

Two sentences, front-loaded with what is returned before the usage trigger. No filler and every clause adds routing or scope information.

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?

A zero-parameter, read-only lookup with no output schema; the description fully covers what an agent needs to decide to call it and what to expect back. Nothing material is missing.

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 no parameter semantics to explain; the baseline for a 0-param tool applies. Nothing in the description misleads about inputs.

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 ('Returns factual information about Ariadne') and enumerates the exact content covered: what it does, target audience, pricing, and ethics/privacy rules. It is unmistakably distinct from siblings audit_practice_footprint and write_sample_google_post.

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 clear triggering condition: 'Use when someone asks what Ariadne is or whether it fits their practice.' It does not explicitly rule out the sibling tools by name, but the trigger is unambiguous enough to route correctly.

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?

Beyond the annotations (readOnly, idempotent, open-world), the description discloses ethics constraints (no client stories, no outcome promises, no review requests, CTAs to the practice site), caching behavior (per-website, 30 days), and a per-caller rate limit (5 new posts/day). These are meaningful operational traits the annotations do not carry.

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: what it does, the constraints/ethics, and the usage context plus operational limits. Every clause carries information, and the core action 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 single-parameter, read-only tool with no output schema, the description covers purpose, ethics guardrails, cache behavior, and rate limits. An agent has everything needed to decide to call it and understand the outcome constraints.

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 100%, so the parameter's format is documented in the schema. The description adds that the tool reads the 'public practice homepage' and implies the URL must be the practice site, which slightly enriches the schema description. With only one parameter and full coverage, the baseline is a 3, but the added context about what the URL represents earns a 4.

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 opens with a precise verb-and-resource pair: it 'reads' a homepage and 'writes' one Google Business Profile 'What's New' post, with an explicit length range (150-300 words). This is distinct from the sibling tools (auditing footprint, fetching an overview), so an agent can tell immediately what this tool does that no sibling 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?

It specifies the trigger clearly: 'Use when a therapist wants an example post or help getting started posting on Google.' That is a concrete condition. It does not name an alternative or state when-not-to-use, so it falls short of a 5, but the context is unambiguous.

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