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

Annotations only declare readOnlyHint=true, so the description carries the rest and does so well: it discloses the empty-result behavior ('Answers none held'), the conditional presence of version_count/source_count/first_edition_seen/last_edition_seen for multi-form records, and staleness reporting for records not printed by a current catalog. Pagination behavior is left 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?

The purpose is front-loaded, but the body sprawls across long, tangled sentences dense with undefined jargon ('the build', 'the Union', 'FORM', 'edition') that an agent cannot resolve from the text. Several clauses explain row shape in prose that would be better delegated to an output 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?

With no output schema, the description does attempt to cover return semantics, the empty case, and conditional fields, which is the right instinct. However, its opaque vocabulary and missing pagination/ordering behavior leave the agent with an incomplete and partly unparseable picture for a multi-record list tool.

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 limit, query, offset and unitid. The description restates the query and unitid filters but adds no format or syntax detail (e.g., how title words are matched, whether UNITID combines with query), so it does not exceed the schema baseline.

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 question states a specific resource (articulation/transfer agreements) and its two filter axes (title words, institution UNITID as a party), which is a clear verb+resource. It also implicitly separates itself from the one-record sibling by noting that forms 'come from the one-record get, never from a list.' The garbled register ('the build holds none', 'current FORM') keeps it from a 5.

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 routing hint that forms are fetched via get_agreement and never from a list is genuine when-to-use guidance, but it is buried mid-paragraph and phrased indirectly. There is no explicit statement of when a caller should reach for find_agreements versus get_agreement, find_transfer_frameworks, or find_pathways among the many siblings.

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