ARVX

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that by stating 'Costs nothing,' which addresses the cost concern an agent or user would have before invoking. It does not describe the shape of the returned content, but for a zero-parameter informational tool the added cost disclosure is meaningful.

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?

Information is front-loaded and every clause carries content: the resource, the return contents, the trigger conditions, and the cost. The opening sentence is a long enumerated list, which is slightly dense, but there is no filler or repetition.

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 simple zero-parameter guidance tool with no output schema, the description fully covers what the agent needs: what will be returned (link, steps, price, key setup) and when to call it. No gaps remain that would cause a misinvocation.

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?

The tool takes no parameters and has 100% schema description coverage, so the schema baseline applies. There is nothing parameter-related for the description to add or omit.

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 spells out exactly what the tool returns: the signup link, the steps the person must take themselves, the price, and how to add the key to this connector. That specificity makes it trivially distinguishable from siblings like arvx_record_summary and arvx_run_reading, which are data-retrieval tools.

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?

It gives two explicit trigger conditions: 'Call this when there is no key, or when the person asks how to start.' No inference is required about when to invoke it, and the conditions are precise enough to act on directly.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new behavioral facts: it consumes no Reading credit and is capped at '10 a month per account'. That quota disclosure is exactly the kind of context annotations cannot carry, though permission/auth requirements and response shape are not covered.

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 short sentences, front-loaded with the use-case trigger, then inputs, then the quota caveat. Dense and mostly waste-free, with only slightly telegraphic phrasing ('Needs the record and both people's emails').

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 4-parameter, all-required tool with nested objects and no output schema, the description covers purpose, inputs and quota but omits the semantics of 'reason' and the expected format of the 'record' identifier. Annotations handle the safety profile, so the remaining gap is moderate rather than severe.

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%, so the description must compensate. It names 'the record and both people's emails', loosely covering record/user/other, but the required 'reason' parameter and its access_request/correction/deletion_check enum are never explained, leaving a meaningful gap.

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 ('returns every item in a saved record in plain words') and frames the user-facing trigger. It implicitly distinguishes itself from arvx_run_reading by noting it 'Never uses up a Reading', though the boundary against arvx_get_access is left unstated.

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 a clear situational trigger ('When someone asks what is held about them'), which is exactly the context an agent needs to pick this over the other record tools. It does not state explicit exclusions or name the alternatives it is contrasted with.

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

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.