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

No annotations are provided, so the description carries the full burden. It discloses that Meridian manually checks every report, nothing changes until verified, a reference like MT-1042 is returned for later use, an API key is required, and there is a 50 reports/day cap. These are exactly the behavioral traits an agent needs.

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-loads the core action and required data, but is a single long sentence with multiple clauses. Information density is high and every sentence earns its place, though the structure could be tightened with paragraph breaks or bullets.

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?

For a 10-parameter mutation-like reporting tool with no annotations and no output schema, the description covers purpose, when-to-use, required inputs, data sources for reference IDs, return value (reference like MT-1042), follow-up usage (check_issue), auth, rate limit, and the manual-review process. Nothing essential is missing.

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. The description goes beyond the schema by explaining how to name a record (registration_id from get_registration/get_registrations, or manufacturer_id, or registry_key such as 'TH_FDA:64-2-1-2-0001234') and that source_quote must be verbatim. It adds practical meaning to several parameters, though not every field is elaborated.

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 ('Tell Meridian that a record... looks WRONG') and the exact record types and fields that can be reported. Clearly distinguished from siblings like check_issue, get_registration, and find_predicates, which handle retrieval or follow-up rather than reporting.

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 when to use it ('wrong data, not for questions about what a field means') and when not to, and names check_issue as the downstream tool that consumes the returned reference. It also states required inputs (what, where) and constraints (API key, 50/day).

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