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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds nothing behavioral: no pagination, no filter semantics, no result shape, no rate limits — the bar is lower with annotations but the description still contributes zero.

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?

The text is short but wasteful: the same endpoint string appears twice verbatim, and the operation ID plus meta-instruction consume the remaining space. Nothing is front-loaded except a path that is already implied by the tool name.

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 nested-object, zero-coverage schema with no output schema, the description leaves an agent unable to construct a valid call without first invoking describe_operation. It does at least name that escape hatch, which is the one genuinely useful piece of information present.

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% and there are two nested-object parameters (query, params) with additionalProperties looseness. The description does not explain what can go in 'query' or 'params'; it only defers to describe_operation, which is a pointer rather than parameter meaning.

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 description restates the raw HTTP path twice and adds nothing beyond the tool name, which already encodes 'get asc842 reconciliation runs'. An agent can infer this is a list endpoint from the path, but there is no stated verb, scope, or distinction from siblings such as get_asc842_reconciliation_runs_by_runId_*.

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?

No when-to-use guidance is given, and the sibling tools (the three by-runId variants, get_asc842_reconciliation_records_by_re*) are never mentioned. The only routing hint is the pointer to describe_operation for request schemas, which is about mechanics rather than tool selection.

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