Admit Coach — College Search & Costs

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

Annotations mark the tool as read-only, idempotent, and non-destructive. The description adds valuable context beyond that: dates come from current-cycle institution records and may lag, students should verify on official pages, and no student data is read or stored. This is strong behavioral 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?

The description is three sentences with no wasted words: it front-loads the main purpose, then adds the prep schedule and calendar URL, then the data-freshness caveat and privacy note. The parenthetical schedule details are relevant and concise.

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?

Given that an output schema exists and annotations already cover safety and read-only behavior, the description provides sufficient operational context: college limit, returned artifacts, data lag warning, confirmation recommendation, and privacy. Nothing essential is missing for correct selection and 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?

The only parameter, unitids, is described in the schema as an IPEDS institution ID from search results, which provides core meaning. The description reinforces the 20-college limit but adds no further parameter detail. With 0% schema description coverage in the prose, the description is minimally adequate but does not substantially improve on 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 clearly identifies the tool as retrieving application, aid, and commitment deadlines for up to 20 colleges, with countdowns and a prep schedule. It is distinguished from sibling tools like get_financial_aid and get_university_details by its focus on deadlines.

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 when to use it—when deadline info and a prep schedule are needed—but it does not explicitly contrast with sibling tools or state when not to use it. No alternative routing or exclusion conditions are 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, and the description's 'Read' aligns with these. The description adds valuable behavioral context beyond annotations: it discloses that figures may not apply to nonresident students and that missing figures remain unknown, which helps the agent set expectations about data completeness and applicability.

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 tight and front-loaded: the first sentence states the core purpose, and the following sentences each add essential caveats without redundancy. Every sentence earns its place, and the length is appropriate for the tool's complexity.

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 a single fully-described parameter and an output schema present, the description does not need to explain return values. It covers the essential context: historical scope, non-applicability caveats, and data-completeness behavior. The tool is simple, and nothing needed for correct invocation 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 sole parameter unitid is fully described in the schema as 'IPEDS institution ID from search results,' so schema coverage is 100%. The description adds no additional parameter-level detail beyond referring to 'a college,' so the schema carries the semantic burden.

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 specific verb and resource: 'Read historical average net price, income brackets, grants and debt for a college.' This distinguishes it from search_universities by focusing on financial aid data, but it does not explicitly contrast itself with get_university_details, so sibling differentiation is only implicit.

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 provides strong contextual guidance by warning that cohort statistics are not a personalized cost estimate or aid offer, and by advising verification via the official net-price calculator before affordability decisions. However, it does not explicitly say when to prefer this tool over get_university_details or search_universities, so the when-to-use advice is implicit rather than directly routed.

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 indicate readOnly, idempotent, and non-destructive behavior, so the description adds value by noting that values are historical and may be missing, that the returned school URL should be cited, and that no login or personal documents are accessed. This enriches the agent's understanding beyond the structured hints.

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 short sentences, front-loaded with the core purpose, followed by usage guidance and caveats. Every sentence earns its place 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 one-parameter lookup tool with an output schema and read-only annotations, the description fully covers the key operational context: how to get the ID, what data is included, data freshness limitations, citation behavior, and access restrictions. 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?

The schema already describes unitid as 'IPEDS institution ID from search results' with 100% coverage, so the description adds little new parameter-level meaning. The instruction to use search_universities first reinforces the source of the ID but does not substantially go 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 uses a specific verb ('Read') and names the exact data categories (admissions ranges, majors, costs, outcomes) plus the lookup key (IPEDS ID). It clearly distinguishes itself from search_universities, which resolves names, so an agent can tell the tools apart.

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 instructs the agent to use search_universities to resolve a name first, which is direct when-to-use guidance. It also sets expectations about data currency and access boundaries, making the invocation context clear.

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, the description explicitly states concrete behavioral boundaries: it returns at most 20 institutions, links to school profiles, searches only public institutional records, does not access student accounts, and does not predict admission. This gives the agent a strong safety and scope profile without contradiction.

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 three sentences with no wasted words: the first defines search dimensions, the second defines result shape, and the third defines data-source boundaries and non-behaviors. The core purpose is front-loaded and each sentence adds distinct value.

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 description covers search dimensions, result limits, and explicit exclusions, which is strong for a read-only tool with an output schema and rich annotations. However, it does not clarify whether multiple filters are combined with AND or OR, and it leaves the meaning of max_acceptance_rate as an upper-bound filter slightly implicit.

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 compensates by mapping each parameter to a concept: name to query, two-letter location to state, field of study to major, acceptance rate to max_acceptance_rate, and the 20-result cap to limit. It does not detail exact formats or default values, but it provides enough meaning for correct invocation.

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 'Find colleges' and identifies specific search dimensions: name, two-letter location, field of study, and historical acceptance rate. It clearly describes a search/listing tool, and the return cap of 20 institutions with profile links distinguishes it from the detail and financial-aid sibling tools, though it never names those alternatives 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 verb 'Find' and the listing-oriented return shape imply this tool is for discovery, not for retrieving individual school details or financial aid data. However, there is no explicit when-to-use or when-not-to-use guidance referencing the sibling tools, so an agent must infer routing from context.

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