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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely useful context beyond that: the account/scope prerequisite, that credentials and identity are never arguments, and the interpretation caveat that an empty blocking_gaps does not establish visa eligibility. That last point is exactly the kind of overreach guard an agent cannot get from structured fields, though it is buried in dense prose.

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?

The section enumeration is front-loaded and useful, but the body is a run-on chain of clauses mixing return-value detail, workflow instructions, and caveats. Standalone fragments like 'Unknown facts remain unknown.' are cryptic rather than economical, and the workflow guidance is interleaved with output-field description where it does not belong.

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 an output schema present and annotations covering the safety profile, the definition supplies what is still needed: auth/scope prerequisites, section selection, and the pre-calculation check workflow. It spends words describing blocking_gaps and scope_gaps contents that the output schema likely already carries, and it omits any guidance on the required dossier_id, which is the one real completeness gap.

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 description coverage is 0%, so the description must carry the burden. It explains the `section` values well and clarifies the default, but `dossier_id` — the only required parameter — is never described; its format, where it is obtained, and whether it must come from create_planning_dossier or list_planning_dossiers are left unstated. Half the parameter surface is therefore well served and half is not.

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 opening clause gives a specific verb plus the four resources it can return (summary default, profile, settings, questions), which maps one-to-one onto the `section` enum. It is easy to separate from create_planning_dossier on the read/write axis, but it never distinguishes itself from get_planning_calculation or list_planning_dossiers, so sibling differentiation is implied rather than stated.

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 concrete trigger guidance: 'Check before a requested calculation; ask targeted questions for blockers, save replies and recheck,' plus 'Read current arrays/revision before edits.' That is a real when-to-use rule with a follow-up loop. It stops short of naming the specific sibling to call when saving replies or fetching a calculation, so the routing is left partly to inference.

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