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

Adds substantial context beyond the annotations: an owner:va authorization requirement, disclosure that saved facts are 'not a live check' and carry a verified_at plus freshness indicator, and interaction rules (ask returned questions one at a time, accept unknown or skip, preserve explicit false). The annotations already cover read-only/idempotent safety, so this is complementary rather than duplicative; it does not describe rate limits or what the returned question objects contain.

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 core action and the optional-records condition before the operational rules and exclusions. It is dense with short imperative clauses; every clause carries a constraint, though the staccato fragments make it slightly harder to scan than a couple of well-formed sentences.

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, the description still tells the agent what comes back (questions to ask one at a time) and what provenance to surface (va_source.verified_at and freshness). Authorization, optional-input gating, and non-goals are all covered, so an agent has enough to invoke it 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 67%, so the schema carries most field documentation, but the description adds real semantic rules the schema lacks: unknown answers are acceptable and skippable, explicit false must be preserved rather than treated as missing, answers stay bound to the same property, and connected VA records are used only when the user claims them. These constraints change how an agent should populate 'answers' and 'skipped_fields'.

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 ('Review requirements for the selected property') and scopes the inputs precisely: accumulated answers plus, only on request, the connected applicant's saved VA facts. It also draws a hard boundary against adjacent capabilities ('does not decide eligibility or savings, generate an application, or file anything'), which separates it from siblings like generate_veteran_packet and get_owner_review_details.

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?

Gives a clear triggering condition for the optional path ('only when requested'), a prerequisite ('Requires owner:va'), and explicit exclusions of what it will not do. It stops short of naming a sibling tool to use instead for packet generation or eligibility, so routing is implied by the exclusions rather than stated.

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