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

With no annotations, the description carries the full burden and does unusually well: it decodes the evidence-grade vocabulary (origin/custody/measured/none), warns that some data is explicitly not held, and reports the outcome of the last fetch of the port's own website. Remaining gaps are failure behavior — what happens when the query matches nothing or matches multiple ports — and confirmation that this is a read-only lookup.

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?

Purpose is front-loaded in the first clause and every subsequent clause adds substantive content about returns rather than filler. It is dense — compressed into essentially one long sentence with many parenthetical clauses — which costs some scannability but wastes no words.

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 lookup tool with no annotations and no output schema, the description adequately characterizes the return payload, including provenance and negative-space information an agent would otherwise have to discover by calling. It falls short only on the multi-parameter input model and on not-found/ambiguity behavior.

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 67%; the description restates that `query` accepts a name, UN/LOCODE, or WPI number, which the schema already says. It says nothing about the undocumented `unlocode` parameter or how the `port` alias relates to `query`, leaving a genuine ambiguity (which field wins if both are supplied).

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 resource (one port) and enumerates what is returned: WPI identity fields, evidence grade, coverage gaps, last website fetch. An agent can tell this is a per-port detail/lookup tool. It does not, however, distinguish itself from siblings like shipping_port_calls or shipping_port_coverage, which sound adjacent.

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?

The closest thing to guidance is the invocation instruction to pass a port name, UN/LOCODE, or WPI number as `query`. There is no explicit when-to-use, no named alternative for movement data (port_calls) or coverage gaps (port_coverage), and no exclusions. Usage is only implied by the enumeration of returned content.

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