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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), and the description adds genuinely useful behavioral context beyond them: it flags LGPD-sensitive health data, states which fields come back (names, contacts, CPF), and explains the paging contract. It stops short of saying what happens with no filters (full dump) or the default page size, both of which affect how an agent drives it.

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, zero filler, with the filter scope front-loaded before the data-sensitivity and paging notes. Every sentence carries distinct information an agent needs.

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 eight params, no required fields, no output schema and only hint-level annotations, the description covers what the tool returns and how to page, which is the right level of detail. The absent piece is behavior with no filters applied and the next_offset/offset naming mismatch, both of which could trip up an agent on first call.

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 every filter, its pattern and defaults, making 3 the baseline. The description adds little parameter-level meaning beyond naming the same filters, and it introduces mild confusion by telling the agent to pass "next_offset" while the actual parameter is named "offset".

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?

"Registered patients, filtered by ..." names the resource and enumerates the five filter dimensions, so an agent immediately knows this is a filtered patient listing rather than a single lookup. The verb is implicit and it never contrasts itself with feegow_get_patient or feegow_list_patient_dependents, which is the only gap.

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 by the filter list plus the note to pass the previous reply's next_offset for paging, and source_id points to feegow_list_patient_sources as a prerequisite lookup. There is no explicit when-to-use-this-vs-get_patient guidance and no statement of whether filters combine or are mutually exclusive, which matters with eight optional params and zero required.

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