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

With no annotations, the description carries the full burden and does real work: it discloses that a single call aggregates multiple data domains, that output must preserve each record's scope and each task's limits, and imposes a hard constraint against converting results into probabilities, scores, or year counts. It omits whether the operation is read-only, any auth requirements, and rate/limit behavior, which keeps it below a 5.

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 the usage trigger, followed by a dense but purposeful enumeration of return contents and closing behavioral constraints. Every clause maps to something the agent needs, though the middle sentence is long and could be broken up for scanability.

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 no output schema and no annotations, the description must carry return-value and safety context, and it describes the return shape in detail plus the interpretation constraints. It still leaves the locale parameter undefined and doesn't state side-effect/read-only status, so it is strong but not fully complete for a 3-parameter aggregator.

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 only 33% (only occupation is documented in the schema), so the description must compensate, and it does for two of three parameters: occupation accepts the person's own words in any language or a slug, and taskIds is explicitly optional and scoped to tasks the person actually performs. The locale parameter is never mentioned in either place, leaving one gap.

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?

The description names a specific verb (get) and a composite resource (an action brief), then enumerates exactly what the brief contains: task trajectories with evidence strength, legal/regulatory retention factors, employer movements, and transition paths. This clearly distinguishes it from narrow siblings like find_transition_paths or find_evidence by positioning it as the aggregate, one-call answer.

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?

It gives an explicit trigger condition with a quoted user utterance ("I'm an accountant, how do I stay employable?"), which is strong when-to-use guidance. It does not name sibling alternatives or state when to prefer them (e.g., find_transition_paths for paths only), so the routing guidance is clear but incomplete.

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