landed

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

With no annotations, the description carries the full burden and does disclose a non-obvious behavioral trait: the call performs a NEW live fetch of the target URL right now, not just a replay of stored data. It also discloses the access model ('public-by-id: anyone holding the receipt_id can re-check it'), which is a meaningful privacy/sharing property. It still doesn't state whether the fresh fetch can fail or cost anything, or how failures surface.

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 sentences, front-loaded with the primary action and the fresh-recheck twist before the usage guidance. Every sentence contributes, though the parenthetical about CDN caches and the final sharing sentence make it slightly denser than needed.

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?

Covers purpose, triggering conditions, the live-recheck behavior, and the sharing model — good coverage for a one-parameter tool with no annotations. With no output schema, however, the description never says what a receipt actually contains or what the recheck result looks like, which an agent reasoning about the return value would want.

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% and the single parameter's format ('hex string returned by verify_write') is already documented in the schema. The description reinforces the provenance of the ID but adds no new syntax or constraint beyond it, so the baseline 3 for schema-documented params applies.

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?

Names a specific verb and resource ('Fetch a receipt ... plus a FRESH recheck') and explains what the receipt is and where it came from (verify_write), which cleanly separates it from the sibling verify_write that produces receipts. An agent can tell the two apart 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 two concrete triggering conditions — the write was still propagating (CDN caches, eventual consistency), or an operator asks for proof of a past write. It names the producing tool but never says when this is the wrong choice (e.g., no receipt exists yet, or when to just re-run verify_write instead), so the when-not side is missing.

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?

With no annotations, the description carries the full burden and delivers meaningful traits: results are newest-first, capped at 100, and consist of signed receipts with statuses. It omits permission/auth requirements and what happens when a log is longer than 100 entries.

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 tight sentences: scope first, then use cases, then return shape. Every sentence earns its place 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 simple one-parameter read tool with no output schema, the description covers scope, ordering, cap, and content type of the return. The remaining gap is truncation/pagination behavior beyond the 100-receipt cap.

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% for the single 'agent' parameter, so the schema already documents it. The description's 'under an agent name' only restates that, adding no new semantics such as format or matching rules.

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 ('read the last receipts filed under an agent name') plus ordering ('newest first'), which is far more than the name alone conveys. It is distinguishable from the singular sibling get_receipt by explicitly scoping to a list of receipts per agent, though it never names the siblings.

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 usage contexts: audit yourself before reporting success, or review what another agent claimed it verified. That is clear when-to-use guidance. It stops short of naming alternatives or stating exclusions (e.g., when to prefer get_receipt instead).

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?

With no annotations, the description carries the full behavioral burden and does so well: it discloses the independent-server fetch, signed receipt, public-by-id re-checkability, 60-calls-per-agent-per-hour rate limit, public http(s) requirement, robots.txt compliance, and honest fetch identification. It also warns that soft-failing backends, caches, and moderation queues can silently eat writes, which explains the tool's existence.

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 description is front-loaded with purpose and then structured into core behavior, call rules, parameter advice, receipt details, and limits. It is dense and largely earns its length, though the opening rhetorical question and dramatized success-message sentence could be trimmed slightly without losing meaning.

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 no-annotation, no-output-schema tool with five parameters, the description covers the behavior, call discipline, return semantics (signed receipt with fresh HTTP status and content match), and operational constraints thoroughly. An agent has enough information to invoke it correctly and interpret the result.

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 meaningful nuance for the expect parameter: it must be a unique substring and without it the receipt only proves page loads, not that the write is present. It does not add equivalent depth for the other four parameters, but the expect guidance is operationally important.

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 action—fetching the written URL from an independent server to verify a write actually landed—and distinguishes itself from get_receipt by positioning that sibling as the later re-check mechanism. An agent can tell what this tool does without opening the 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?

Explicitly says to call it once after a write and not to poll, gives the intended trigger context (post, comment, edit, upload, deploy), and names get_receipt as the alternative for later re-checking. This is clear when-to-use and when-not-to-use guidance.

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