xi.pe

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

With annotations all set to false, the description carries the full burden of behavioral disclosure. It states the 2 MiB limit and that oversized input is rejected (not truncated), mentions that the delete_token appears once and is the only deletion mechanism, and specifies the returned fields. This covers key operational behavior an agent needs.

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 compact yet complete. It front-loads the core purpose, bundles use-case triggers, then covers size limits, return values, and the delete-token special case, and ends with a markdown-readability tip. Every sentence adds value with no padding, and the structure logically flows from purpose to practical usage.

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?

Given the tool's moderate complexity (3 parameters, 1 required) and the presence of an output schema, the description covers everything an agent needs: what to store, size policy, when to use it, return fields, the one-time delete token, and a formatting tip. No critical operational detail 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 description coverage is 100% – every parameter (content, ttl, long) has a clear description including defaults and constraints. The tool description adds no extra parameter-specific meaning beyond what is already in the schema; it reiterates size limits and mentions the TTL default, but these are already documented. Since the schema is comprehensive, a 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 opens with a specific verb and resource (Store UTF-8 text at xi.pe and get back a short URL), clearly distinguishing the action from its sibling tools (read_paste and delete_paste). It also states the output format (url, code, delete_token, size, expires), making the tool's purpose unmistakable.

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 explicitly lists concrete triggers ('share this', 'give me a URL for it'), conditional cases (long diffs, stack traces, configs, reports that would flood chat), and cross-context needs (another agent/session/machine without shared filesystem). It also advises on handling the delete_token when a human is in the loop, giving clear direction on when and how to use the tool.

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?

The description adds value beyond the annotations by explaining the necessity of the delete_token for ownership proof, and noting that deletion can occur before the paste's natural expiration. The destructiveHint annotation is confirmed. However, the description could also mention if the operation is irreversible or if it affects other users, but given the annotations already indicate destructive and idempotent behavior, the description is largely sufficient.

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 two sentences, no wasted words. The first sentence front-loads the action and timing constraint, the second explains the key prerequisite. 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?

Given the tool has only 2 required parameters and no nested objects, the description is complete. It explains the action, timing, and authentication requirement. It could be more complete by describing what happens upon success (e.g., confirmation message) but the absence of an output schema makes this acceptable.

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. The description adds value by explaining why the delete_token is required ('provides proof of ownership') and clarifies that code can be a short or long code or full URL. This goes beyond the schema's basic descriptions, justifying a score of 4.

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 uses a specific verb ('Delete') and resource ('a xi.pe paste'), clearly distinguishing it from siblings like create_paste and read_paste. It also adds the important context that deletion can happen before expiration, which clarifies the scope beyond a simple delete.

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 explicitly states when to use this tool (to delete before expiration) and what prerequisite is required (the delete_token). It implies when not to use it—if you lack the token, you cannot prove ownership—which is a clear exclusion criterion. No sibling tool is mentioned, but the token requirement effectively distinguishes it.

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 read-only nature is covered. The description adds useful behavioral context: it accepts both code and full URL, and it explains the ?md rendering behavior for Markdown. It doesn't mention rate limits or response format, but for a simple read tool with readOnlyHint, the description adds meaningful value beyond 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?

Three sentences, each earning its place: the first states the core function, the second clarifies input flexibility, the third gives a practical usage tip. No fluff or repetition of schema details.

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 read tool with one parameter, full schema coverage, and readOnlyHint annotation, the description is nearly complete. It covers what the tool does, input formats, and a rendering tip. It doesn't describe the return format, but with no output schema and a simple text-fetch operation, that's a minor 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?

Schema coverage is 100%, so the schema already documents the 'code' parameter well. The description adds value by clarifying that the parameter accepts either the 6-character code or the full URL, and by explaining the ?md suffix behavior. This goes beyond the schema's description, which only says 'the paste's code... or its full xi.pe URL'.

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 states the tool fetches the text of an existing xi.pe paste, with a specific verb ('Fetch') and resource ('text of an existing xi.pe paste'). It also distinguishes itself from siblings by mentioning it can read pastes handed over by users or agents, and the sibling tools (create_paste, delete_paste) are clearly different operations.

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 explicitly says when to use it: to fetch an existing paste, including one just handed to you. It also provides a conditional usage tip: if passing the URL to a human and the text is Markdown, append ?md. It doesn't explicitly name alternatives, but the sibling tools are create and delete, so no alternative read tool exists; the usage context is clear.

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