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

Annotations already declare readOnly/openWorld/non-destructive, so the description's job is added context, and it delivers: Starter plan or higher is required, matching is fuzzy and homonym-prone, and each result carries role counts plus up to three current companies. It does not discuss result ordering or cost of broad queries, but the added behavioral context is well above the annotation baseline.

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 sentences, each carrying distinct load: what it searches, what it returns and how to disambiguate, and the plan requirement. Front-loaded with the core action and no filler.

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?

No output schema exists, and the description compensates by describing the return shape (enhedsnummer, current/former role counts, up to three current companies). With fuzzy matching, homonym risk, and plan gating all covered, an agent has what it needs to call this correctly.

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 baseline is 3, but the description adds real meaning to `query` that the schema lacks: partial names are accepted and small misspellings are tolerated. The `limit`/no-paging behavior is left entirely to the schema, which already documents it.

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 and resource (search people in the Danish company register) and scopes it to name-based lookup, which cleanly separates it from get_person (single-record fetch) and search_companies (company lookup) among the siblings. The chaining hint that results carry the enhedsnummer get_person needs further pins down its role in the toolset.

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?

Explains the search semantics (partial names work, small misspellings tolerated) and gives concrete guidance on ambiguity: compare the listed companies before concluding two hits are the same person. It also names the downstream tool (get_person) and the plan prerequisite. It stops short of explicitly saying when NOT to use it (e.g. exact single-person lookup), which keeps it from a 5.

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