PayPerFax

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

The description carries far more than the annotations (readOnlyHint=false, destructiveHint=false) convey: no charge at creation time, payment happens in the browser, email confirmation only arrives after payment, a "failed" status means no charge and a retry is possible, and markdown text is capped at 100 KB with images reduced to alt text and raw HTML to plain text. The only gap is the exact shape of the returned link/response beyond "a link".

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 opening paragraph front-loads the what and the what-not, and the numbered rules make it scannable. It runs long, though, and rule 7 restates the "nothing is sent and nothing is charged before they pay" point already made up top, plus the embedded curl recipe is arguably documentation for a different call than this tool.

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?

With no output schema, the description takes on the burden of explaining the return value — a link for the person — and then describes the full downstream flow (preview, price, payment, sending, failure handling). For a 13-parameter tool with only one required field, it gives an agent everything needed to call it and to instruct the person afterwards.

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, but the description adds real meaning on top: rule 2 explains the operational purpose of file_expected (the person adds the file on the link page), rule 4 warns that a long cover_message is cut off, and rule 5 explains how markdown is rendered into print. The remaining parameters (country, timezone, language, cover_page, sender_name) are only covered by the schema.

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 ("Prepare a fax") and immediately delimits scope: it does not send and does not charge, it returns a link the person uses to pay and send. That framing cleanly separates it from get_fax_status (which reports on an already-created fax) without needing to name the sibling.

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?

Seven numbered rules give explicit when-and-how guidance: ask for email rather than guessing, use file_expected for documents the person already has instead of retyping, take fax numbers from official sources and show the person, use markdown for letters you write, and fall back to a raw curl call when a local file exists and shell commands are available. Nothing about selection or prerequisites 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.

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

Beyond the readOnlyHint annotation, it discloses the whole state machine an agent will encounter: pending/delivered/failed/expired plus substages rendering, awaiting_payment, sending, including that price/pages can still change while unpaid. It also explains side effects of failure (no charge, resend possible, render_failed needs a link) and expiry, which is exactly the context annotations cannot carry.

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 core action is front-loaded in the first clause, followed by input sourcing and then status semantics. It is dense but nearly every clause carries distinct information; the status enumeration is long, yet each term is defined rather than merely listed.

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?

With no output schema, this description essentially serves as one, defining every status and stage value an agent must interpret. Nothing needed to call it correctly or read the result is missing.

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 accepted formats are already documented, but the description adds practical provenance ("the status address from the tracking prompt of the person") that tells an agent where to obtain the address, not just what shapes are legal. That is real value over the schema, though the field itself is a single string.

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?

"Read where a fax is" states a specific verb and resource, and the description ties the input back to create_fax, so an agent knows this is the follow-up read to a freshly created fax rather than a listing tool. It is clearly distinct from list_supported_formats.

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 concrete invocation timing ("read the status when the person asks") and an explicit exclusion ("Do not call this in a loop"). It stops short of naming an alternative polling mechanism or another status tool, but the when/when-not guidance is clear.

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 already declare readOnlyHint=true, so the safe read profile is covered. The description adds that the result is a catalog of accepted inputs and limits, but does not describe the response shape, pagination, or whether the list is static.

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?

A single front-loaded sentence that leads with the action ('List what PayPerFax can fax') and then enumerates the covered dimensions. No filler or redundancy.

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?

There is no output schema, but the description effectively previews the return contents (text, file types, sizes, languages), which covers what an agent needs to know. A brief note on when to invoke it would close the remaining gap.

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 zero parameters, so the baseline is 4. There is no parameter surface to disambiguate and the description correctly implies no inputs are required.

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 ('List') and resource (supported fax formats), and enumerates the dimensions covered: text input, file types, sizes, and languages. It also loosely distinguishes itself by referencing create_fax's inputs and the HTTP call path, which helps separate it from the sibling 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?

Usage is only implied: a reader can infer this is a reference/discovery call to make before create_fax, but the description never says 'call this first' or when not to bother. No explicit alternative or exclusion is given.

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