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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's job is to add beyond that. It does: it discloses that the tool returns 'ids, short stems and alignment, never answers' (a meaningful boundary), that result includes filter lists, and that it is 'Cheap' (a cost cue). These are concrete behavioral traits not derivable from annotations.

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 dense and front-loaded, leading with the core action and resource before layering scoping and return-format details. Every sentence carries information, though the filter enumeration runs slightly long and could compress the parameter list already present in the schema.

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 12-parameter tool with an output schema, this is close to complete: it names the subject scope, the type/filter dimensions, the AP Calc variant rule, the excludeAssigned behavior, and the answer-free return contract. An agent has enough to call it correctly, with only pagination and sibling disambiguation left unaddressed.

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?

With 67% schema coverage, the baseline is 3, but the description adds genuine semantic value: it explains that courseVariant scopes AP Calc AB to exclude BC-only units, topics and FRQs, and that unit/topic/skill must be exact labels drawn from the returned filter lists (a cross-call dependency). It does not explain offset/limit pagination, so it stops short of a 5.

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 ('Searches Fiveable's question bank') and scopes it to one subject, enumerating the four question types and the filter dimensions. It also grounds the tool by noting it is 'the same bank as the assignment builder,' which helps route the agent. It does not, however, distinguish itself from the sibling search_content, which an agent could easily confuse with it.

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 rather than stated: the reference to the assignment builder and 'optionally hiding questions this teacher already published' convey the intended context, and the note that filters accept exact labels 'from the filter lists in the result' implies chaining. There is no explicit when-to-use vs. when-not, and no named alternative such as search_content or get_questions_for_materials.

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