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

With no annotations, the description carries the full burden and does so well: it discloses sort semantics, exclusion rules for PMA supplements and bulk loads, and the latency profile. It stops short of covering what happens when limit truncates results or whether there is pagination, which is the remaining behavioral gap.

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?

Front-loaded with purpose and scope, and every sentence carries actionable content — exclusions, meta reporting, and performance. It is dense and the final sentence runs long, but nothing is padding.

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?

There is no output schema, so the description must explain the return shape, and it does: ordering, the meta.basis.bulkLoadsExcluded field, and the instruction to repeat meta.basis.note rather than claim completeness. That is exactly the guidance an agent needs to report results honestly.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning on top: it explains that `markets` filtering has a large performance payoff and that `days` is defined by first-seen date rather than approval date. `risk_level` and `device_type` gain no extra context beyond their schema enums.

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?

States a specific verb+resource ('Registrations newly added to Meridian in the last N days') with the competitor-monitoring framing, which distinguishes it from the broader get_registrations sibling. The ordering rule ('by when we first saw the record, not approval date') further pins down what the tool actually returns.

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?

Explicitly says what is out of scope (US PMA supplements, bulk-loaded records) and why, and names the meta fields that report the exclusions. It also gives a concrete selection rule for the markets filter: unfiltered is ~15s, one or two markets ~1s.

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