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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds only that results are 'bounded' and what fields are returned; it says nothing about ordering, why 'header confidence' matters, or what a low-confidence header implies for downstream use.

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?

Two short sentences, front-loaded with the payload the agent gets back. The second sentence is thin but not wasteful; nothing is repeated from annotations.

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 does compensate by listing the returned fields, which is genuinely useful. But for a list tool among many similar siblings it omits pagination semantics, ordering, and the meaning of 'header confidence', leaving real gaps.

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 load, yet it never mentions pagination, the default page size of 25, the max of 100, or offset limits. 'Bounded' is the only hint, and the unusual nesting of limit/offset inside a required 'input' object is left unexplained.

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 verb 'Read' plus the returned fields (table names, row counts, header confidence) tells the agent what comes back, but the resource itself — what a 'handwritten summary' is — is never defined. It also gives no differentiation from the near-identical sibling list tools (list_bank_statement_summaries, list_import_vat_summaries, list_rate_confirmation_summaries, list_vendor_statement_summaries).

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?

'Source-file exports are a separate workflow' is a partial exclusion, but it names no alternative tool (e.g. export_saved_document) and gives no condition for when this list should be called. There is no guidance at all for choosing between this and the other *_summaries listing tools.

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