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

Adds quota/cost behavior the annotations do not convey: 'Costs one Reading (the first 3 are free).' It also instructs saving the returned record, which is essential state-management context. Annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) are consistent with a non-destructive metered computation, and the description enriches them rather than repeating them.

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 purpose in the first sentence, followed by tightly packed operational rules. Every sentence carries distinct, actionable information with no filler.

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, complex-input tool with no output schema, the description covers preconditions, cost, and record round-tripping well. The only gap is that the return value is only obliquely referenced ('the record from the answer'), leaving the exact output shape for the agent to discover.

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 100%, so the baseline is 3; the description adds value by specifying email ordering and minimum-per-sender requirements for the emails array, and the exact semantics of the record parameter (must be the prior Reading's output, unchanged). It stops short of explaining the user/other object fields, which the schema already covers.

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: 'Run a Reading on two people from the emails between them.' Clear what it does, but it doesn't differentiate itself from the sibling tools (arvx_get_access, arvx_record_summary), leaving the agent to infer the routing.

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?

Explicit preconditions ('at least 3 emails written by the user and 3 by the other person, oldest first') and an explicit rule for repeat invocations ('From the second Reading on a pair, send the record from the last Reading exactly as it was returned'). The agent knows exactly when to pass record and when to omit it.

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