CollegeCalcAI

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

Annotations already establish read-only, idempotent, closed-world behavior, so the safety profile is covered. The description goes beyond that by enumerating the response contents (percentage, Reach/Target/Likely/Safety verdict, factors that would move the number, federal admissions data, calculator link), which is valuable because there is no output schema.

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 scope, then the return payload. Nothing is wasted and no sentence is redundant with another.

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 14-parameter, read-only estimator with no output schema, the description covers the action, the required input class, and the full return shape, so an agent can call it correctly. It stops short of explaining how partially-specified inputs are handled (e.g. gpa vs weightedGpa precedence, defaulted grade/round), which the schema covers only per-field.

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 one of the 14 parameters is already documented with ranges, enums and defaults. The description only restates categories ("GPA, test scores and context") and adds no format, precedence, or defaulting detail beyond the schema — baseline 3 is correct.

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+resource pair ("Estimate a student's chance of admission") and pins the scope to "one U.S. college," which cleanly separates it from the sibling estimate_college_list and find_colleges_for_score. The inputs (GPA, test scores, context) are named so an agent knows what it must supply.

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 single-school scope but never made explicit: there is no "use this when you have a specific school in mind, use find_colleges_for_score when you don't" routing, and no prerequisites or exclusions. Adequate for an agent that already knows the tool family, but it does no routing work.

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, so the safety profile is covered. The description adds genuinely useful behavioral context that annotations cannot: it enumerates what comes back (schools sorted by chance with verdicts, Reach/Target/Likely balance, chance of at least one acceptance, balancing advice).

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, no filler, and the scope constraint ('up to 15 colleges at once') is front-loaded before the return-value detail. Every clause carries 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?

For a 14-parameter tool with no output schema, the description does the important work of describing the return payload, and the schema fully covers inputs. What is missing is any caveat about the estimates being probabilistic/approximate or guidance on the required 'schools' list versus the optional profile fields.

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 14 parameters are already documented with ranges, enums, and defaults (e.g. ACT ignored if SAT given, grade defaults to 12). The description adds nothing about parameter semantics beyond the 15-school cap, 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 verb ('Score'), the resource (one student profile against colleges), and the batch scope ('up to 15 colleges at once'). The batch framing implicitly separates it from the single-school sibling estimate_admission_chances, but that sibling is never named, so the agent must infer the distinction.

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 phrase 'up to 15 colleges at once' implies this is the bulk-list variant, which is the main usage cue. However, there is no explicit when-to-use guidance, no statement of when to prefer estimate_admission_chances over this tool, and no prerequisites or limits beyond the count.

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 a read-only, idempotent, non-destructive, closed-world operation, so safety is covered. The description adds useful behavioral detail beyond that: it discloses the data basis (each college's real admitted-score data) and the response shape (counts plus example colleges per tier).

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?

Front-loaded with the user question it answers, then scope, data source, and return content in a tight single paragraph with no filler. The nested quotes in the opening clause are slightly awkward but the structure is otherwise efficient.

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 usefully explains the return value (counts and examples per tier). Annotations cover the safety profile. A minor gap: with zero required parameters, the description never states what happens if no score/GPA is supplied, which would help an agent avoid an empty call.

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 each parameter is individually documented with ranges and 'if no SAT'/'if no test score' conditions, so the schema does the heavy lifting. The description's 'one SAT, ACT or unweighted GPA' lightly reinforces the mutually-exclusive-input intent but adds little the schema doesn't already convey. Baseline 3.

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 (buckets every covered U.S. college into safety/target/reach/high reach) for a specific input (one SAT, ACT or unweighted GPA), tied to the exact user question it answers. However, it never distinguishes itself from siblings like estimate_college_list or estimate_admission_chances, which an agent would need to choose between.

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 phrasing 'Answer "what colleges can I get into with a ___"' implies the usage context, but there is no explicit when-to-use guidance, no exclusions, and no mention of the four sibling tools it competes with. Usage is inferable but not spelled out.

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 safety and determinism are covered structurally. The description adds genuine context beyond that by disclosing the data source ('Federal') and that part of the payload is a derived estimate rather than raw reporting. It says nothing about data vintage, coverage gaps, or caching, so it is useful but not rich.

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 leads with the resource and then enumerates payload contents, with the differentiator ('No student profile needed') placed last. Every clause carries retrieval-relevant content and there is no 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 correctly compensates by listing the return fields, which is the key completeness requirement here. The remaining gap is metadata about the data itself — reporting year, whether every U.S. college is covered, and how the GPA/SAT chance estimate is derived.

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% and there is a single required 'school' string, so the schema already carries the parameter burden. The description only clarifies that no student profile input is required, which is mild added meaning; it offers no guidance on name format (e.g., full name vs. campus/ID).

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?

Names a specific verb (get) and resource (federal admissions and outcome data for one U.S. college) and enumerates the exact fields returned: applicants, admits, yield, SAT/ACT middle 50%, test policy, cost, net price, graduation rate, earnings. The closing clause 'No student profile needed' implicitly separates it from estimate_admission_chances, so an agent can route 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 a clear usage condition: use this when you want a school's aggregate data and have no student profile. It does not explicitly name or exclude alternatives (estimate_admission_chances, search_colleges, find_colleges_for_score), so the when-not side is left 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, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral value beyond them by explaining the SAT ranking semantics (distance from the student to each school's 75th percentile) and by disclosing the return payload (names intended for the estimate tools), which matters because there is no output schema. Pagination and default ordering without a SAT score remain unstated.

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 purpose, then the ranking behavior, then the output handoff. Every clause carries information and none is redundant with the title or annotations.

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 7-parameter, zero-required search tool with no output schema, the description covers purpose, ranking semantics, and the returned value, which is what an agent most needs. Remaining gaps are minor: no statement of how results are ordered when no SAT score is supplied, and no mention of filter combination behavior.

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 86%, so the baseline is 3. The description earns above baseline by explaining the SAT parameter's ranking mechanism in more depth than the schema's terse 'Rank results by SAT fit', and by covering the undocumented type parameter as public/private. It does not explain how the acceptance-rate bounds interact.

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 names a specific verb and resource (find U.S. colleges) and enumerates the filter facets (name, state, public/private, acceptance-rate range), so the tool's scope is immediately legible. It hints at the downstream relationship with the estimate tools, but never contrasts itself with the closest siblings find_colleges_for_score or get_school_admissions_data, so sibling differentiation is only partial.

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 gives real usage context for one mode: supplying a SAT score ranks schools by proximity to the 75th percentile, and the returned names feed the estimate tools. However, there is no when-not-to-use guidance and no explicit statement of when to prefer this tool over find_colleges_for_score or get_school_admissions_data, leaving the choice to inference.

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