Special Needs Care Network

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

Goes well beyond the annotations by explaining the matching service mechanics: it is free, surfaces a few providers with availability that accept the family's insurance, spares the family from calling anyone, and returns a private confirmation link. This describes the practical outcome of the call, which readOnlyHint/idempotentHint alone would not convey; the family-initiated confirmation at the link keeps it consistent with readOnlyHint=true.

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?

Four tight sentences, front-loaded with the resource and coverage scope before the usage cue and return behavior. Every sentence carries information, though the care-type enumeration is partially redundant with the enum schema descriptions.

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 matching tool with no output schema, the description supplies geography (US), coverage scope, trigger conditions, and the return value (a private link), which is exactly what an agent needs to set expectations. 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 every parameter is already documented, including the care_types enum values. The description only restates the care type vocabulary and adds no extra semantics (e.g., how zip vs. state interact, or what happens when insurance is omitted), so the baseline of 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 verb and resource ('Find special needs care in the US') and immediately enumerates the four covered care types (ABA, special needs schools, speech therapy, diagnostic testing). This makes it easy to separate from the sibling tools, which concern cost estimation and IEP goals rather than provider matching.

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 trigger conditions: 'Use when someone asks for help finding care, a provider that takes their insurance, or a special needs school near them.' It lacks explicit when-not guidance and never routes the agent to get_aba_therapy_cost for pricing questions, so it falls short of a 5.

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 this is a read-only, idempotent, non-destructive lookup. The description adds useful behavioral context by listing the categories of information returned, going beyond what the annotations provide. It does not describe data provenance or freshness, which keeps it from a 5.

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 the action and returned data, followed by a clear usage trigger. There is no redundant or filler wording.

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 lookup, the description covers what the tool returns and when to use it, while annotations cover safety and idempotency. It could be slightly more complete by mentioning data vintage or source, but nothing essential 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%, and the single state parameter is well documented with examples. The description reinforces that the tool works for a US state or DC, but adds no syntax or formatting meaning beyond what the schema already provides.

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, 'Get,' and names the exact resource categories returned: private-pay rates, intensive monthly estimates, insurance mandate details, and Medicaid access notes. It also scopes the tool to a US state or DC, making its purpose immediately clear and distinct from the unrelated sibling 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?

It explicitly says when to use the tool: when someone asks what ABA therapy costs or whether insurance or Medicaid covers it in a state. It does not name alternatives or exclusions, but the sibling tools cover different domains, so this is a clear usage context without needing sibling 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 readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds value by disclosing the shape of the result (areas with descriptions and goal counts), which matters since there is no output schema; it does not mention result size or whether the list is exhaustive.

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 with no filler; the resource comes before the details of what is returned. Nothing is wasted and nothing essential is buried.

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 zero-parameter, closed-world read tool with full annotation coverage, the description supplies the one missing piece: what a returned area looks like. The only gap is the absent hand-off to search_iep_goals for drilling into goals, which an agent would have to guess.

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 (empty object schema with additionalProperties false), so there is nothing for the description to disambiguate. Baseline 4-5 applies and the description stays consistent with the no-argument contract.

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?

"List the skill areas in the IEP goal bank" gives a specific verb and resource, and adds what each entry contains (descriptions and goal counts). It does not distinguish itself from the sibling search_iep_goals, so an agent must infer the browse-vs-search split.

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: a zero-parameter list tool is naturally a discovery/browse call, but the description never states when to reach for this instead of search_iep_goals, nor what to do with the returned areas afterwards.

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 establish the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the description needn't restate safety. It adds meaningful behavioral context by disclosing the shape of each returned goal — condition, observable skill, criterion, measurement method, timeframe — which is valuable given there is no output schema. It does not mention result ordering, empty-result behavior, or the relationship between browsing and querying.

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, each carrying distinct load: what is searched, what a result contains, and when to use it. Front-loaded with the verb and resource, and no filler or restatement of 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 four-parameter search tool with no output schema, the description covers purpose, result anatomy, and usage context, which is enough to call it correctly. Minor gaps remain around how query and area interact and what happens with no matches, but nothing essential 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 all four parameters are already documented, giving a baseline of 3. The description's skill examples ('requesting a break, AAC, reading fluency, or transition planning') loosely illustrate the vocabulary that maps onto the query and area parameters, but it adds no syntax, matching behavior, or guidance on combining query with area.

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 ('Search') and a precisely scoped resource ('a bank of complete, measurable example IEP goals'), plus concrete skill examples (requesting a break, AAC, reading fluency, transition planning) that make the content type unmistakable. It does not differentiate itself from the near-sibling list_iep_goal_areas (which enumerates areas rather than goals), so it stops 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?

Provides a genuine usage trigger: 'Use when drafting or reviewing IEP goals.' That gives the agent a clear context for reaching for this tool. It offers no exclusions or alternative routing, so an agent must infer on its own whether to call list_iep_goal_areas first when it doesn't know the available areas.

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