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

Annotations only declare readOnlyHint, so the description carries real weight and delivers: source precedence (held rules first, then CourseAtlas read live), the 'comparable, never equivalent' semantics, and conditional output behavior (version_count/source_count/first_edition_seen only appear for multi-form records, and stale records self-report). It adds no auth, rate-limit, or error behavior, but the data-provenance disclosure is genuinely useful beyond the annotation.

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 length is defensible given there is no output schema and the row-shape rules must be conveyed somewhere, but the prose is convoluted and back-loaded: it opens with a rhetorical question and then stacks run-on clauses about FORM wording sources and edition spans. It is not clearly front-loaded, though little of it is pure 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 and a fairly complex, 9-parameter query, the description does the heavy lifting on returns: it explains row fields, the source-per-form rule, the conditional multi-form fields, and the stale-record case. The main gap is pagination/ordering behavior (limit/offset exist but only the schema explains them) and the absence of any alternative-tool routing beyond a passing mention.

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 the schema already documents all nine inputs (code, title, school, unitid, direction, limit, offset, etc.). The description's detail is almost entirely about OUTPUT fields (source_url, band, version_count), not inputs, so it adds little input-side meaning beyond what the schema provides — the 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?

The opening line ('Where does this course land at other schools, and what lands on it') and 'The published transfer rules for one course' make the resource and the direction of the query clear. However, the jargon ('the rules CourseShelf holds', 'band', 'FORM') obscures rather than sharpens the purpose, and no sibling tool is named for contrast, leaving the agent to infer how this differs from get_comparability or find_comparability.

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 only implied: the tool is for pulling transfer rules per course, and there is one routing hint ('The forms themselves ... come from the one-record get, never from a list') pointing to a sibling. There is no explicit when-to-use / when-not statement and no named alternatives among the ~50 siblings, so the agent must infer the boundary.

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