Wayback Machine

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

Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds concrete behavioral detail: it returns the snapshot URL, exact timestamp, raw-bytes URL, and optionally stripped page text capped at 30k chars, plus the fallback to Common Crawl. It does not cover every edge case, like no capture being found at all, but goes well beyond the annotations.

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 three sentences with no fluff. It front-loads the core function and return fields, then quickly covers fallback behavior and use case. Every sentence earns its place.

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 properly explains return values (snapshot URL, timestamp, raw-bytes URL, optional text) and fallback behavior. It is nearly complete for a read-only archive lookup, but it omits edge-case behavior such as what happens when neither WayBack nor Common Crawl has a capture.

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 schema already documents all parameters (100% coverage), so the baseline is 3. The description adds meaningful detail for parameters, such as explaining that timestamp selects the nearest capture and that fetch_text returns HTML-stripped text capped at 30k chars, which enriches the schema without duplication.

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 function: retrieve the closest archived copy of a URL from the Wayback Machine, with a clear resource and action. It also distinguishes itself from the sibling tool by emphasizing a single closest snapshot rather than a capture history, and notes the Common Crawl fallback.

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 explicitly says when to use the tool: 'Use when a page is dead, changed, or walled and you need what it said.' This provides clear context, though it does not mention when not to use it or explicitly reference alternatives like capture_history.

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 establish read-only, idempotent, non-destructive behavior, so the description's additional context about filtering by status/MIME, collapsing, date-window restriction, and paging adds useful behavioral detail. It does not describe the exact output format or any rate/volume caveats, but the annotations cover the safety profile and the description reveals the query scope well.

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?

Two sentences carry a compact description of scope, capabilities, primary use cases, without fluff. The key scoping idea is front-loaded ('Every capture...') and the 'Use for...' sentence gives practical grounding.

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 complex tool with 10 parameters and no output schema, the description does most of the work by explaining what kind of data is returned and why an agent would want it. It could specify the output format or field semantics more explicitly, but the CDX-index reference and the strong schema give sufficient context for correct selection and invocation.

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 schema already documents every parameter thoroughly. The description reinforces important concepts like collapse, date windows, and resume keys, but adds little meaning beyond what the parameter descriptions already state; the baseline of 3 is appropriate.

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 clearly identifies the resource (Wayback Machine captures, CDX index) and the main operation (retrieving all captures for a URL, prefix, host, or domain). It is easy to infer that this is a history/listing tool rather than a snapshot-retrieval tool, but it stops short of an explicit imperative verb like 'List' and does not directly contrast with sibling archived_copy.

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?

The description gives a clear intended use, 'site archaeology: what a site ever had, when a page changed, every URL under a path,' which tells the agent when to call it. It does not explicitly state when not to use it or mention archived_copy as the alternative for fetching a specific archived page, so exclusions are missing.

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