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

Annotations already declare readOnly/destructive/openWorld, so the safety profile is covered; the description adds genuinely non-structured behavior: that view filters and sorts are implicitly applied and that filter narrows rather than overrides them, plus that results carry total and nextOffset for paging. It does not discuss the limit/offset interaction or any truncation behavior, which is the main remaining gap.

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?

Three tight sentences, each earning its place: capability, mechanism selection plus view interaction, then return shape. The performance hint is front-loaded inline with the parameter names rather than buried.

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 9-parameter read tool with nested filter objects and no output schema, the description covers the semantics an agent most needs (filter vs formula, view interaction, paging). Missing sort/field-projection guidance and the absence of any return-shape note beyond total/nextOffset keep it from being complete.

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?

With schema coverage at 56% and nine parameters, the description compensates meaningfully: it explains the filter-vs-formula semantic split, supplies a concrete Airtable formula example for the otherwise undescribed formula parameter, and clarifies offset via 'nextOffset for paging'. Sort, baseId, and the filter conjunction remain unexplained anywhere, so it is strong but not complete.

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 ('Find records in a table') and immediately scopes how matching works. It is clear against write-oriented siblings like create_records/delete_records, but it never distinguishes itself from get_records, which likely fetches by id, so an agent must infer the boundary.

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 concrete selection guidance between the two query mechanisms: 'filter (structured, fast)' vs 'formula (... slower)', which is exactly the decision an agent faces. It also explains the view interaction rule ('the view's own filters and sorts apply and filter narrows them'). It does not name a sibling alternative or a when-not-to-use case, so it stops short of a 5.

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