InWithYou Guide

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

The description goes beyond the annotations by explaining that readOnlyHint is true because it reads bundled, human-verified data with no network calls or state changes, and that openWorldHint is false because it never touches external systems. This is useful transparency. However, it simply restates the annotation values rather than adding behavioral details beyond them, such as rate limits or caching behavior.

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 front-loaded with the core purpose, followed by usage constraints, and closes with annotation explanations. Every sentence earns its place without 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 2-parameter read-only tool with no output schema, the description covers purpose, usage, and behavioral traits well. It does not need to explain return values since the output schema is absent, but it could mention pagination or result limits. Overall, it is nearly complete for an agent's needs.

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 schema already documents both parameters thoroughly, including the enum values and the scoping rule. The description doesn't add any new parameter semantics beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 (searches), the exact resource (InWithYou non-medical guides), the scope (one condition by topic), and the return fields (title, excerpt, audience, URL). It clearly distinguishes itself from siblings like match_resources or get_resource_detail by emphasizing bundled, human-verified guide content.

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 explicitly says when to use this tool ('lead with guide content before asking the user anything') and when not to ('Never use for diagnosis, treatment advice, drug information, or symptom interpretation; redirect medical questions to the clinician'). It also implicitly distinguishes from siblings such as match_resources, which likely serves a different matching purpose.

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?

Adds real behavioral constraints beyond the annotations: an id from another condition's partition is 'rejected, never served', and the tool is scoped strictly to family/life topics with medical questions redirected. However, the closing three sentences restate readOnlyHint, destructiveHint and openWorldHint almost verbatim, which duplicates structured data an agent already has.

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 first half is front-loaded and efficient, correctly leading with the payload and the match_resources sequencing. The second half balloons: three sentences re-explain annotation flags that are already supplied as machine-readable structured data, adding length without new 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?

No output schema exists, and the description compensates by enumerating the returned fields. It also covers scope limits (non-medical), the condition-partition constraint, and the intended call sequence, so nothing an agent needs to invoke it correctly 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 coverage is 100%, so the baseline is 3 and the schema already documents both parameters thoroughly. The description still adds meaning the schema does not: the cross-partition rejection rule for resource_id, which tells the agent an id paired with the wrong condition will fail rather than be served.

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 the full vetted record for one resource by its id within one condition') and enumerates the payload fields (description, coverage, cost model, referral mechanics, last-verified date). It clearly positions itself as the follow-up to match_resources, so an agent can distinguish it from siblings without opening the schema.

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 sequencing ('Use after match_resources when the user wants more detail on a specific listing') and an explicit when-not-to-use rule ('Never use for diagnosis, treatment advice, drug information, or symptom interpretation; redirect medical questions to the clinician'). Both the trigger and the exclusion are stated rather than 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?

Annotations already declare readOnlyHint, destructiveHint, openWorldHint, and idempotentHint, so the safety profile is covered structurally. The description goes beyond by explaining the source of the data ('bundled, human-verified data', 'makes no network calls') and by enforcing a non-medical scope with a redirect policy, though the trailing hint restatements largely duplicate the annotation block.

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 opening sentence and the 'call this first' routing rule are front-loaded and earn their place, but the final two sentences re-explain readOnlyHint and destructiveHint and openWorldHint at length, which the agent already has from annotations. That is redundant padding that dilutes the otherwise tight definition.

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 burden of describing the return value and does so explicitly (three hubs, display names, guide/resource counts). Combined with the routing rule and scope limits, an agent has everything needed to call it correctly.

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 no parameters, so there is no per-argument semantics to supply; the baseline for a zero-parameter tool is 4. The description correctly implies the tool is called without input and its output is fed into subsequent tools.

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 and enumerates the exact contents returned: 'the three InWithYou condition hubs (MS, Parkinson's, Alzheimer's/dementia) with display names and guide/resource counts.' An agent immediately knows what this tool yields, distinct from find_guides or match_resources.

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 an explicit sequencing rule ('Call this first when the user's condition is unclear, then pass the chosen condition to every other tool') plus clear when-not boundaries ('Never use for diagnosis, treatment advice, drug information, or symptom interpretation') and a redirect instruction.

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?

Adds real behavioral context beyond annotations: the privacy constraint (never include names, ZIP codes, or health details) and the 'call once' rule are not derivable from the annotation block. The sentences restating readOnlyHint/destructiveHint/openWorldHint are largely redundant with the annotations and add rationale rather than new information.

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 core instruction and privacy rule are front-loaded and earn their place, but roughly half the text is spent restating annotation values (readOnlyHint, destructiveHint, openWorldHint) that already appear in structured form, diluting the description.

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?

Covers the trigger, the payload to report, and the privacy constraints for a 4-parameter, fully required, fully documented tool with no output schema. It leaves the post-call return behavior unstated, but that is a minor gap for a reporting 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?

Schema description coverage is 100%, so the schema fully documents condition, need_summary, found, and gap, including the enum scoping guidance. The description's mapping to those fields adds no syntax or format detail beyond what the schema already provides, 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?

States a specific action (report/log what the user sought, whether resources met the need, and content gaps) at a specific moment (once, when the conversation ends). This is clearly distinguishable from find_guides, match_resources, or list_conditions, which are lookup tools rather than outcome reporting.

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 precise trigger: 'Call once when the conversation ends,' which tells the agent exactly when to invoke it. However, it stops short of explicit exclusions or naming a sibling alternative, so it does not reach the top band.

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?

Adds real behavioral context beyond the annotations: free/nonprofit ranking that cannot be outranked by paid referrals, a verbatim disclosure line for referral-flagged resources, and the ZIP is never stored or transmitted. However, the final three sentences largely restate readOnlyHint/destructiveHint/openWorldHint already present in structured annotations, diluting the added value.

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 core purpose is front-loaded, but the description runs long and spends three full sentences re-explaining annotation hints that the agent already receives as structured fields. That redundancy keeps it from being tight.

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 four required params, no output schema, and annotations present, the description covers everything an agent needs: result count, ranking policy, filtering via ZIP, disclosure obligations, privacy, and domain boundaries. Nothing material is missing 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds parameter-relevant meaning: national resources always match regardless of state, and condition scoping never blends results across conditions. This goes modestly beyond what the schema documents.

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 2-4 vetted resources for a need category within one condition') plus the ranking basis and domain scope, so the function is unmistakable. It does not explicitly name or contrast with siblings like find_guides or get_resource_detail, so it falls short of the explicit-differentiation bar.

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?

Provides explicit when-to-use (need category scoped to a single condition) and when-not-to-use ('Never use for diagnosis, treatment advice, drug information, or symptom interpretation; redirect medical questions to the clinician'). Also instructs re-calling on condition switch rather than blending contexts, leaving little to inference.

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