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.