Quantabble — AP Science Misconception Diagnostics

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

With no annotations, the description carries the full burden and does so: it enumerates the return payload (verdict, misconception, error_source, curriculum position, scoring rationale, required elements, teaching move, probe question, tutor_response), explains error_source semantics, and warns not to read reader_trap verbatim. This is rich behavioral disclosure beyond structured fields.

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 purpose and return payload, then reuses for integration advice and disclaimers. It is dense and long, but each clause carries information. The curriculum_anchor aside is slightly tangential but not wasteful.

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-param tool with no output schema and no annotations, the description is thorough: it lists the return fields, explains follow-up usage, and sets input constraints. It omits latency/cost behavior and explicit error-handling guidance, which keeps it short of a 5.

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 documents both parameters, putting the baseline at 3. The description adds meaning: it explains the practical value of schema_id (skip routing across 130 schemas, faster/more consistent, pair with curriculum_anchor for reporting) and clarifies student_response should be the student's own words, not a paraphrase.

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+resource (diagnose a student's written explanation) and scopes it precisely to AP Chemistry / AP Physics 1 reasoning. It distinguishes itself from the only sibling, get_coverage, which is a different operation entirely.

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?

Explicit when-to-use: any free-response reasoning in AP Chem / AP Physics 1. Explicit when-not: 'not for single-word or numeric answers' and requires at least one full sentence. It also names the follow-up workflow (pass schema_id back).

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?

With no annotations, the description carries the full burden and does disclose useful behavior: it is free and triggers no model call, and 'Returns' implies a non-mutating read. It does not state auth requirements, whether the catalog is cached/stale, or pagination behavior, so it falls short of fully covering the missing annotation profile.

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, zero waste, and the core capability is front-loaded before the usage guidance. Every clause earns its place.

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, so the description correctly compensates by summarizing the returned structure and noting the free/no-model-call cost profile. For a parameterless read tool, an agent has everything needed to call it and route its result.

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 zero parameters, so the baseline is 4. The description still adds value by clarifying what schema_id means and where it should be passed (diagnose_response), which is meaning beyond the empty 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?

States a specific verb and resource ('Returns Quantabble's coverage and full topic catalog') and enumerates the returned fields (schema_id, course, unit, topic number, title). This distinguishes it clearly from the sibling diagnose_response, which consumes rather than supplies the schema_id.

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 two concrete when-to-use conditions (verify a topic is in scope; look up the schema_id to pass to diagnose_response when the student's topic is already known) and explicitly names the sibling tool to hand off to. Nothing about selection 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.