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

Annotations already declare readOnlyHint=true, so the safe-read profile is covered. The description adds one genuine behavioral fact beyond that — an empty result set is reported as 'none held' rather than an error — but says nothing about pagination behavior even though offset/next_offset semantics exist, leaving that to the 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?

Three short sentences, front-loaded with the core question the tool answers, with no redundant boilerplate. The phrasing of the final clause ('Answers none held when the build holds none') is slightly awkward but still compact and information-dense.

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 zero required parameters, full schema coverage, and no output schema obliging the description to explain return values, the definition covers both filter dimensions and the empty-result behavior. Only the missing routing against get_agreement/find_transfer_frameworks keeps it from being fully complete.

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 all four parameters (limit, query, offset, unitid) are already documented in the schema. The description restates query and unitid but adds no syntax, format, or default detail beyond what the schema provides, so the baseline of 3 applies.

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: looking up which articulation or transfer agreements are held, and describes the two filter axes (title words or a party UNITID). However, it does not distinguish itself from the near-name siblings get_agreement or find_transfer_frameworks, 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?

It signals the intended search modes ('optional title words, or an institution's UNITID as a party'), which implies the tool is a filtered lookup rather than a by-ID fetch. But it never states when to use this instead of get_agreement (single lookup) or find_transfer_frameworks, so routing between the two find-tools 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.