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

Annotations already declare non-readonly, non-destructive and idempotent, so the safety profile is covered. The description adds real behavior beyond them: each file starts a new page, inter-file links are preserved, a single outline is produced, and optionally a table of contents. It does not say what happens if a listed file is missing or whether the source files are modified.

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 short sentences, front-loaded with the core action, then the input constraint. The parenthetical '(and with toc one table of contents)' is a bit cramped but each element still earns its place. No filler or restatement of the tool name.

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 17-parameter rendering tool with an output schema and full schema coverage, the description supplies the essential mental model: many Markdown files in, one structured PDF out, with inputs constrained to a single folder. Remaining gaps, such as missing-file handling and whether rendering requires external tooling, are minor given the rich schema.

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 all 17 parameters thoroughly, including the SUMMARY.md/folder/file-list forms of inputs. The description's one added constraint, that listed or folder-held files must lie in that folder, adds genuine meaning for the inputs parameter but is terse and slightly ambiguous. Baseline 3 is appropriate when the schema carries nearly all semantics.

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 and resource: 'Makes one PDF of several Markdown files', with the multi-file scope, page-break, link-preservation and outline behavior spelled out. It implicitly separates itself from markdown_to_pdf (singular) by emphasizing 'several' files, but never names that sibling, so the differentiation is left for the agent to infer.

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: the tool is for compiling a book of Markdown files into one PDF. There is no explicit statement of when to prefer this over markdown_to_pdf, and no mention of prerequisites or failure modes. The final sentence reads as an input constraint rather than routing guidance.

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 non-read-only, idempotent, non-destructive, closed-world, so safety is covered. The description adds real behavioral value beyond that: it discloses the rendering support matrix and, more importantly, an explicit degradation list (CSS/HTML layout, LaTeX packages, non-flowchart Mermaid, script-dependent SVGs) plus the return values, so an agent can predict silent quality loss. It does not mention performance, file-size limits, or failure modes, which keeps it below 5.

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 first sentence is well front-loaded, but the remainder is one long run-on catalogue of syntax features with semicolon-and-comma chaining that is hard to scan. Much of that catalogue is duplicated by the referenced resource rayomd://syntax, so the listing is informative but not tightly curated.

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 19-parameter converter with an output schema and full schema coverage, the description covers what matters: purpose, capability envelope, degradation, and a pointer to a resource for the exhaustive syntax list. Only the missing sibling routing and parameter-interaction notes keep it from being complete.

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 baseline is 3, and the description meaningfully exceeds it: it explains that relative image paths resolve from the Markdown file's folder (clarifying how path vs markdown vs source_path interact), and it ties dialect to concrete syntax sets (obsidian callouts, ==highlights==, [[wiki links]]) and diagrams to the Mermaid types actually drawn. It still does not explain interaction between toc, toc_depth and a [TOC] paragraph, or defaults for the boolean flags.

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 ('Converts Markdown ... to a PDF with RayoMD') plus the return payload (page count and warnings). The scope (text or file, single document) is distinguishable from siblings like book_to_pdf and recover_markdown, and the supported/dialect surface tells an agent exactly what class of document this handles.

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 implied by the purpose but never stated: there is no guidance on when to pick this over book_to_pdf, or when recover_markdown should come first. The closest thing to routing guidance is the parameter-level hint 'give this or path' / 'give this or markdown', which helps invocation but not tool selection.

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?

Goes well beyond the annotations: it discloses the ~1s polling/reload cycle, the condition under which a rewrite is picked up (changed on disk and no unsaved buffer edits), and the hard prerequisites (rayomd-gui on PATH or RAYOMD_GUI_PATH, a desktop session, Wayland on Linux). The readOnlyHint=true is consistent, since the tool itself only opens a viewer even though the user may edit.

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?

Front-loaded with the action and resource, then prerequisites last, which is the right order. The middle sentence on reload semantics is long and comma-chained, but every sentence carries information an agent would otherwise have to guess.

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?

Return values are covered by the output schema and prerequisites and side effects are well documented. The one real gap is whether the call blocks until the GUI is dismissed or returns immediately, which materially affects how an agent sequences subsequent calls.

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?

With a single parameter at 100% schema coverage ("The .md file to open"), the schema already carries the semantics, so baseline 3 applies. The description adds no path constraints such as absolute vs relative paths or behavior for a nonexistent file.

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 ("Opens a Markdown file in RayoMD GUI") plus the user-facing purpose ("for the user to read or edit"), which cleanly separates it from the sibling converters markdown_to_pdf and book_to_pdf. An agent can pick this over the PDF tools 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?

The clause "for the user to read or edit" makes the intended situation clear: interactive desktop viewing/editing rather than conversion or recovery. It stops short of explicitly excluding alternatives (e.g. "use markdown_to_pdf to produce a PDF instead"), so routing is inferred rather than stated.

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?

Adds real context beyond the annotations: the result is digest-checked, the write target is always a new .md file and never overwrites, and the source PDF is left untouched — which reconciles the apparently write-capable readOnlyHint=false with non-destructive intent. It doesn't say what happens when the digest check fails (error vs. partial output), which is the remaining behavioral unknown.

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?

One tight sentence front-loads the action, then the required input condition, then the output-mode distinction and the non-destructive guarantee. Every clause carries 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?

For a two-parameter tool with a full output schema, the description covers the input precondition, output destination semantics, and side-effect profile. The only omission is failure behavior on a digest mismatch or a non-embedded PDF, which an agent would want to know before relying on it.

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 both parameter descriptions already state the embedded-source requirement and the 'never replaces a file' / 'returned as text if omitted' behavior, so the description largely restates the schema. Baseline 3 applies; no extra syntax or format guidance is added.

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 (recover the Markdown source) plus the scoping precondition — only reversible PDFs exported with the source embedded. That precondition implicitly distinguishes it from the inverse sibling markdown_to_pdf, so an agent can select it without reading 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?

The 'reversible PDF (one exported with the source embedded)' qualifier tells the agent exactly which inputs qualify, and the second clause contrasts returning text vs. writing a file. It stops short of naming what to do when the PDF lacks embedded source (e.g., use an extract/convert tool instead), so the exclusion is implied rather than routed.

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