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

Adds real context beyond the annotations: each call consumes one Reading from a free-then-paid quota, and repeated readings on the same pair are stateful (the previous record must be replayed), which explains the non-idempotent, credit-consuming nature. It does not disclose what happens to the email bodies submitted — notable for an openWorldHint tool that analyzes private correspondence.

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?

Four short sentences, each carrying a distinct operational fact — input composition, ordering, record replay, and cost. No filler, and the core action leads.

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?

Given the tool has no output schema, the description should say more about what a Reading returns beyond implying it is a savable 'record'; the agent is told to save it but not what it contains or how long it takes. Otherwise, for a 4-parameter nested open-world tool, the operational guidance is nearly 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?

Schema coverage is already 100%, so the baseline is 3, but the description adds genuine meaning: the 'at least 3 by each side, oldest first' constraint is stricter than the schema's minItems 1, and 'send the record exactly as it was returned' defines the required fidelity of the record value. It says nothing extra about the nested user/other profile objects or the scores-vs-emails fallback.

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 states a specific verb and resource with scope: run a Reading on two people from the emails between them. It is distinguishable in operation from arvx_record_summary and arvx_get_access by the email-driven input, though 'Reading' itself remains proprietary jargon that the description never defines.

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 preconditions: at least 3 emails written by the user and 3 by the other person, ordered oldest first, and the rule that from the second Reading on the pair you must resend the prior record unchanged. It does not, however, route the agent to arvx_get_access for the 'first 3 are free' check or explain when reading is inappropriate.

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