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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, yet the description still adds real behavioral detail: the default RecordID-ascending ordering that guarantees stable paging, the next_skip paging contract, and the warning that omitting select returns hundreds of columns per row. It omits the response envelope shape, but that is a minor gap against otherwise strong disclosure.

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 mandatory `select` rule, then the two most error-prone syntax surfaces (filter, apply) with examples. Dense but almost every clause carries operational value; the trailing raw endpoint `GET /api/v1/tables/{table}` is the one piece that may not earn its place.

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 7-parameter, output-schema-less query tool with a non-trivial filter/aggregation DSL, the description supplies the syntax, the paging pattern, the default sort and the select requirement. It does not explain the returned fields (rows array vs next_skip vs aggregate result shape), which an agent would still have to discover at call time.

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 the baseline is 3; the description goes beyond it by documenting the OData filter grammar (quoting, date format, operators, functions) with a worked example and by showing both aggregate and groupby forms for `apply`. Only `top`/`skip` semantics are left entirely to the schema, which already handles them.

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 concrete verb+resource ("Query any table") and enumerates the table families it covers, making clear it is the generic table reader. It does not explicitly contrast itself with siblings like method_get_record or method_list_contacts, so an agent must infer that those are single-record or pre-filtered alternatives.

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 in-tool usage rules ("Always pass `select`", "page with next_skip", apply "instead of listing rows") which implicitly tell the agent how to call it. It never says when to prefer this over method_get_record, method_list_* or method_search_customers, so tool-selection guidance is left to inference.

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