RawMark

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

Annotations already establish the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description goes further by disclosing that scanned PDF pages are read by an AI vision model, that `ai_accuracy` incurs paid-plan AI processing for every page, and that each call consumes one conversion from a quota. That quota/plan context is genuinely useful behavior an agent cannot infer from 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 dense sentences, front-loaded with the purpose and formats, followed by input-mode rules and cost/behavioral caveats. Every sentence adds non-redundant information 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?

An output schema exists, so return values need not be described. For a 4-parameter, no-required-arg tool the description covers formats, input modes, AI behavior, and quota cost; only edge cases like size limits or failure conditions are unaddressed, which is acceptable given the structured fields available.

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 0%, so the description carries the burden and mostly succeeds: it explains the two mutually exclusive input modes (url vs content_base64 + filename) and the meaning/cost of ai_accuracy. It does not explain `filename`'s expected format or whether url must be publicly reachable beyond 'a public link', leaving one minor gap.

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?

Specific verb ('Convert') plus resource ('a PDF, DOCX, PPTX, XLSX, HTML or TXT file to Markdown'), with the supported input formats enumerated. An agent immediately knows this is a document-to-Markdown converter and can distinguish it from the unrelated sibling get_usage.

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 clear operational conditions: supply either `url` or `content_base64` plus `filename`, and `ai_accuracy` only applies on paid plans. It stops short of explicit when-not guidance (e.g., file size limits, what to do when the URL is not public), but the invocation paths are unambiguous.

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, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context by revealing the two operating modes (license-key conversions vs today's free conversions), but it says nothing about staleness, rate limits, or auth requirements for the license-key path.

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?

A single compact sentence with no filler, and the key fact (remaining conversions) is front-loaded ahead of the two modes. Nothing could be cut without losing information.

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 an output schema present, the description need not enumerate return fields, and no parameters need documenting. It adequately frames the dual-mode result, though it never states when an agent should call it relative to convert_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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies the license key is not supplied as an argument but resolved from caller context, which prevents an agent from hunting for a missing parameter.

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 verb-plus-resource: it reports what a RawMark plan 'has left' in conversions. That is concrete enough for an agent to distinguish it from convert_document (which consumes conversions rather than reporting them), though the sibling is never named.

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?

Usage is only implied — an agent can infer this is a quota-check tool to call before or instead of converting. There is no explicit when-to-use statement, no mention of the convert_document alternative, and no exclusions.

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