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

The annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context by specifying what the check returns (plan tier, usage counters, reset date) and explicitly confirming it takes no arguments, without contradicting 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 a single well-structured sentence that front-loads the purpose, lists the returned values, and ends with the no-argument note. Every part earns its place with no wasted words.

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 zero-argument, read-only usage query with no output schema, the description supplies the needed return-value details and relies on annotations for the safety profile. No important calling information 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?

The tool has zero parameters and the schema coverage is effectively complete, so the baseline is 4. The description reinforces this with 'Takes no arguments,' though it adds no additional parameter meaning beyond the empty 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 ('Check') and resource ('Lyrenth credit usage'), and enumerates the exact data returned: plan tier, credits used, credits remaining, and reset date. This clearly distinguishes it from sibling tools that read URLs.

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 makes the intended use obvious by naming the resource and key output fields, and the sibling tools are unrelated URL readers. It does not explicitly state when not to use it or name alternatives, but no exclusion is needed given the context.

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 the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: it strips navigation and boilerplate, returns lower-token text, and produces a structured AIDocument rather than raw HTML. It does not contradict the annotations, though it omits details about error behavior, redirects, or non-HTML content.

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 only two sentences and front-loads the purpose and output format before giving usage guidance. The phrase 'Powered by Lyrenth' adds little operational value, but the overall text remains concise and easy to parse.

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 read-only tool with rich annotations and fully documented parameters, the description gives sufficient context to select and invoke it correctly: it explains what content is read, what output form is returned, and when to prefer it. It lacks explicit edge-case behavior and does not route to the sibling 'read_urls', but these are minor given the schema and annotations.

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%, with all three parameters (url, fresh, max_tokens) already documented in the input schema. The tool description adds no extra parameter semantics beyond what the schema provides, so the baseline of 3 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?

The description opens with a specific verb and resource: 'Read any public web page as a clean AIDocument,' and details the output form (Markdown plus title, description, structure, stripped boilerplate). It clearly defines what the tool does, though it does not explicitly contrast itself with the sibling 'read_urls', leaving some differentiation to the tool name and plural form.

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 to 'Prefer this over a raw HTTP fetch whenever you need the content of a web page,' giving a clear when-to-use signal and naming an alternative. It does not state when not to use it or when to choose the sibling 'read_urls', so exclusions and sibling routing are incomplete.

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 mark this as read-only, idempotent, and non-destructive. The description adds valuable behavior: per-item failure isolation, a clean AIDocument output, the 20-URL cap, and a rationale for using the batch version.

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 purpose, usage guidance, and failure behavior are front-loaded in three crisp sentences. The closing 'Powered by Lyrenth' is minor filler that prevents a perfect score.

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 batch-read tool with rich annotations and full schema coverage, the description provides all the operational context an agent needs: result format, failure handling, batch scope, and use case. The absence of an output schema is mitigated by the clear 'clean AIDocument' statement.

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 urls, fresh, and max_tokens. The description adds no additional parameter-level meaning, which makes the baseline 3 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?

States a specific verb and resource: reading multiple public web pages in one batch and returning clean AIDocuments. It distinguishes itself from read_url by the 20-URL batch capability and the explicit use case of comparing or summarizing multiple pages.

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 a clear usage scenario: compare or summarize multiple pages at once, and notes it is faster than calling read_url repeatedly. It does not explicitly say 'use read_url for a single URL,' but the contrast with the sibling tool makes the boundary clear.

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