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

Annotations declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and the description is fully consistent (no contradiction). Beyond that, it adds rich procedural detail: which credential fields are withheld by name, the ownership-reflection derivation of served tables, artifact metadata behavior, the coverage-block contract, and auth requirements. This is exactly the kind of context that prevents a caller from misinterpreting the result set.

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?

Eight dense, information-carrying sentences with zero filler. It front-loads the core operation, then flows logically through exclusions, security withholdings, paging behavior, and non-goals. At ~250 words it's long, but every sentence carries unique weight — the one knock is that an agent must read to the very end to find the auth requirement ('Requires authentication and the account:export scope').

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 security-sensitive, paginated export tool with two parameters and a rich output schema, the description covers all bases: data scope, credential redaction, explicit exclusions with a documentation pointer, the paging protocol, and disclaimers about non-equivalence to erasure or compliance. The only marginal omission — rate limits or response sizes beyond rows_per_model — doesn't rise to a missing gap. A 5.

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 per rubric the baseline is 3. The description adds real value by explaining the truncation contract — 'narrow to one model and raise rows_per_model rather than re-reading everything' — which clarifies both the `models` and `rows_per_model` parameters' operational meaning. It doesn't add syntax details for the `models` enum values, so it's a strong 4, not a 5.

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?

Excellent verb+resource clarity: 'Export this account's own data across every table the account owns' is specific and immediately scopes the operation. The description even explains the envelope format and table derivation. However, while it's clear about what sets this tool apart from generic lookups, it never explicitly distinguishes it from siblings like audit_export — the rubric's 5 requires exactly that kind of explicit sibling differentiation.

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 description gives strong paging and execution guidance: 'Bounded rather than streamed: each model reports truncated and the envelope reports complete, so narrow to one model and raise rows_per_model rather than re-reading everything.' It also clearly states what this is NOT for ('not an erasure request and not a claim of regulatory compliance') and points to docs for exclusions. It stops short of naming alternative tools for specific scenarios, so a 4.

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