find_recalls

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered; the description goes further by disclosing that DateDue and RecallTypeNum filters are applied locally rather than server-side, which explains result counts and why pages can come back empty. The 'follow next_offset even if results is empty' rule is a genuinely useful non-obvious behavior. It does not cover permissions or rate limits, so it is not a 5.

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 primary capability and constraints, with no filler. A minor wrinkle is that the last sentence instructs on 'next_offset', which is not an input parameter and is only meaningful via the output schema, so it reads slightly out of place here.

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?

Output schema exists, so return values need not be explained, and annotations cover the safety profile; what remains for a 6-parameter search tool is filter-combination rules and the date format, neither of which is given. The two operational constraints it does supply (366-day cap, local filtering) are the ones an agent would most likely get wrong, which largely offsets the gap.

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 0%, so the description carries the burden, and it only partially does: it maps 'patnum' to patient, 'recall_type' to the local RecallTypeNum filter, and 'due_date_start'/'due_date_end' to paired inclusive bounds. It never specifies the date string format, whether both bounds are mandatory together, or what limit/offset default to, so an agent must still guess at formats.

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 uses a specific verb ('Read') plus a specific resource ('recall records') and scopes it to a patient or paired due-date bounds. It further distinguishes itself from a superficially similar concept ('the office's Recall List eligibility rules'), which prevents an agent from conflating the two. It does not name a sibling tool as an alternative, so it stops short of 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?

It states the two ways to call it (by patient, or by paired inclusive due-date bounds capped at 366 days) and gives explicit pagination behavior ('follow next_offset even if results is empty'). What is missing is guidance on whether patnum and the date bounds can be combined, and there is no explicit when-not-to-use routing to another tool.

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