Faxbeep

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavior the annotations cannot: the result is the fax object plus a page-1 image when readable, thumbnail_url should be rendered in image-capable chats, and view_url gives the full page. It also documents failure modes precisely — not-found for a new or still-processing fax, and a specific removal message with 30-day retention and deleted files.

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 identification rule and return shape are front-loaded, with error cases and sample tools following in a logical order. A few sentences are expendable, notably 'A client can draw that image very small,' which reads as an aside rather than actionable instruction.

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 single-parameter read tool with no output schema, the description covers everything an agent needs: identifier formats, the shape of a successful result (object plus image), rendering guidance for thumbnail_url and view_url, and the distinct error outcomes for pending versus removed faxes. Nothing material is left to inference.

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 earns credit above it by specifying the slug pattern ('fax_' plus 8 characters from 0-9 and a-f) and noting that view_url may carry a language prefix such as /de. Those details are not in the schema's parameter text and directly reduce invocation errors.

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 ('Get one test fax') and immediately pins down the two accepted identifier forms with a concrete example (fax_1a2b3c4d) and the URL form. It also relates the return value to list_test_faxes ('the same as an item of list_test_faxes'), which lets an agent distinguish it from the listing sibling without opening either schema.

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 clear context: fetch a single fax by slug or view_url, and use fax_example / fax_example_removed when a sample answer is wanted. That is real routing guidance, but there is no explicit statement of when to prefer list_test_faxes over this tool (e.g. 'to enumerate, use list_test_faxes').

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 cover read-only/idempotent/non-destructive, but the description adds substantive context the annotations cannot: every received test is public on faxbeep.com for 30 days (with a privacy warning to relay), the email test may be disabled, and server time must be used rather than the agent's own clock.

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-loads the action and the 'call this first' directive, and nearly every sentence carries operational detail. It is dense and slightly sprawling, with field explanations interleaved with warnings rather than cleanly grouped, but little is wasted.

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 zero-parameter tool with no output schema, the description supplies everything needed: what is returned, how to interpret each field, when data may be missing, and the privacy constraint on the person's test document.

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?

Zero parameters, so the schema baseline is 4. The description goes further and defines the undocumented return fields (local_format vs international_format, email_max_message_bytes semantics with ~1/3 encoding overhead, troubleshooting_url), which matters because no output schema exists.

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 ('Get the Faxbeep test fax numbers, the test email addresses and the limits') and enumerates the payload sections. It also distinguishes itself operationally from list_test_faxes by supplying the 'now' value used as that tool's 'since'.

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 ordering instruction: 'Call this first, before the person sends a test.' It also routes the agent onward ('Use it as "since" of list_test_faxes') and explains the condition under which 'email_addresses' is absent (email test off).

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 cover read-only, idempotent, non-destructive and non-open-world, yet the description adds real behavior: results are capped at "limit" with no paging, an empty list is a normal transient state, new faxes typically appear within a minute but sometimes longer, and entries are public for 30 days before removal. It also warns that a time/sender/page-count match narrows but does not prove ownership.

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-loads what the tool returns, then field-by-field output shape, then polling rules, then edge cases — a sensible order with almost no filler. It is long and repeats "newest first" and re-states the 20-item default that the schema already carries, which keeps it from a 5.

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 carries the full burden and does it: it enumerates every returned field, explains the "since"/"now" envelope values, and defines truncation and retention behavior. An agent has everything needed to call it, interpret an empty result, and report back to the user.

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 meaning beyond the schema for "since" (must come from the server's "now", stay fixed while polling, never be bumped to the newest received_at, covers 24h when omitted) and for "from" (the FAXBEEP-EXAMPLE sentinel that overrides "since", and the note that masked result values must not be reused). The truncation hint about "limit" also tells the agent when to narrow.

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?

Opens with a specific verb and resource ("List the test faxes that Faxbeep received and published, newest first") and adds a scope that separates it from a per-user lookup: the list is public and contains everyone's tests. It references get_test_numbers as the source of a "now" value but never contrasts itself with get_test_fax, so sibling differentiation is only partial.

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 about when to call (polling for an incoming test), how to poll (wait ~30s, stop after ~10min), how to set and hold "since", and what to do with results (show view_url, show thumbnail_url in image-capable chats). It also pre-empts common misuse (don't use your own clock, don't advance since to the newest received_at) and names the FAXBEEP-EXAMPLE path for a sample answer.

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