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

Annotations already declare destructiveHint=true, idempotentHint=true, and readOnlyHint=false, so the mutation profile is known. The description adds genuine context beyond that: it explains WHAT is destroyed ('replaces whatever is currently on the clipboard'), the platform-dependent MIME support (Wayland/X11 vs macOS/Windows), and which MIME types are rejected. This is useful added detail rather than repetition of 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?

Front-loaded with the core action and organized under clear WHEN TO CALL / Args / Returns headers, so an agent can scan it quickly. It is thorough to the point of being slightly verbose (the trigger-phrase enumeration and per-platform MIME notes), but every section maps to a real decision the caller must make.

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 mutation tool, the description covers the action, the destructive effect, trigger conditions, sibling routing, parameter formats, and platform constraints. An output schema exists, yet the Returns section still summarizes the confirmation shape, so nothing needed to call it correctly 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 0%, so the description carries the full burden and does so: it documents that content accepts any string, gives mime_type's default, enumerates supported values (text/plain, text/html, text/rtf, image/svg+xml), and explains the rejection of binary/audio/video types with the correct fallback tool.

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 ('Copy text to the user's system clipboard') and immediately distinguishes it from siblings by naming clipboard_copy_image as the path for binary image types. An agent can tell this apart from clipboard_copy_markdown, clipboard_paste, and clipboard_read_raw without opening any 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?

An explicit WHEN TO CALL section lists trigger phrases ('copy this', 'put this on my clipboard') plus the proactive case (formatted output the user wants outside the conversation). It also names the alternative tool and the exact condition that selects it ('for PNG or JPEG, use clipboard_copy_image'), leaving nothing to inference.

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 (destructiveHint=true, idempotentHint=true, readOnlyHint=false) are consistent with the description, which adds genuinely new behavioral context: the clipboard is overwritten, MIME headers are verified against the declared type, no re-encoding occurs, and a byte-size ceiling keyed to MCP_CLIPBOARD_MAX_IMAGE_BYTES applies. This is well beyond annotation coverage.

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 core action, then cleanly sectioned into WHEN/Args/Returns/Limits, and the Args details are load-bearing given the empty schema. The Returns block is mildly redundant since an output schema exists, keeping it just short of a 5.

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 2-param destructive write with an output schema, the description supplies everything material: trigger conditions, encoding contract, MIME restrictions, size limit and how to raise it. Nothing an agent needs to call it correctly 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 0%, so the description carries the full burden and does: `image_data` is base64 bytes interoperable with `clipboard_paste`, and `mime_type` accepts only image/png or image/jpeg with header verification. Both parameters are disambiguated with syntax and constraints the schema lacks.

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?

Opens with a specific verb+resource: 'Write an image to the user's system clipboard.' It immediately scopes the tool to images and explicitly routes text content to `clipboard_copy`, so the agent can distinguish it from the sibling text tools without reading any 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?

A dedicated WHEN TO CALL section gives trigger phrases ('copy this image', 'put this on my clipboard') plus a second scenario (produced/fetched images to paste elsewhere), and names the alternative `clipboard_copy` for text. Explicit when and when-not coverage.

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 destructive/readOnly/idempotent, and the description goes well beyond them: atomic dual-format placement on macOS/Windows, the Wayland single-MIME quirk where text/plain returns HTML markup instead of markdown source, and the X11 empty-clipboard failure mode. That is exactly the kind of platform-specific behavioral disclosure annotations cannot carry.

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 and organized under clear headers, but the redirect to clipboard_copy is repeated in three separate sections (WHEN TO CALL, Args, and twice under Platform behavior), which adds bulk for a one-parameter tool. Content earns its place but could be tightened.

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, yet the description still sketches the return shape (confirmation with input character count and HTML byte count), and it covers platform variance, escaping semantics, and the correct alternative tool. Nothing an agent needs to invoke or recover from this call correctly 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?

With 0% schema coverage on the single parameter, the description compensates fully: it defines 'text' as CommonMark source, specifies what syntax is supported, and warns that raw HTML is escaped rather than passed through, routing users to clipboard_copy with mime_type=text/html for hand-written HTML.

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+resource (render markdown to HTML, place both formats on the clipboard) and explicitly distinguishes itself from the sibling clipboard_copy by target app type. An agent can select it without opening any 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 'WHEN TO CALL THIS TOOL' block gives explicit trigger conditions with example utterances, an exclusion ('For plain text without formatting intent, use clipboard_copy instead'), and a further fallback for hand-crafted HTML. Nothing is left to inference.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context the annotations do not: passing 'primary' on macOS/Windows returns an error, and the X11/Wayland-specific nature of PRIMARY. It does not discuss latency or rate limits, but for a local clipboard read that is minor.

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 purpose and the routing instruction, then Args/Returns blocks. Efficient overall, but the 'Returns: A list of available clipboard formats' section duplicates a return value already defined by the output schema, so one block is not fully earning 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?

For a one-parameter diagnostic read tool with annotations and an output schema, the description covers purpose, routing, and the platform-specific edge case completely. The only redundancy is restating the return shape that the output schema already supplies, which is harmless rather than a 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 description coverage is 0%, so the description carries the full burden for the single parameter, and it does: the default value ('clipboard'), the exact alternative ('primary'), the platform it applies to (X11/Wayland), and the failure mode on macOS/Windows. This is more meaning than the bare string type in the schema provides.

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 ('List the MIME types / formats currently on the system clipboard') and immediately scopes it as a diagnostic tool distinct from clipboard_paste, which actually returns content. An agent can tell it apart from clipboard_read_raw and clipboard_paste without opening any 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?

Names the alternative explicitly ('use clipboard_paste to actually read and return clipboard content') and gives a concrete motivating scenario (spreadsheet data via text/html or text/plain). It also states the when-not case implicitly through the diagnostic framing, leaving nothing to inference.

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 cover safety (readOnlyHint, idempotent, non-destructive). The description adds real context beyond them: content types handled, table auto-detection, image return as base64 image content, and the platform-specific failure mode for 'primary' on macOS/Windows. Slightly shy of 5 only because it doesn't describe behavior of the raw/format siblings.

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 and well-sectioned (triggers, scope, args), but the trigger-phrase list is long and somewhat redundant. Every sentence is informative, so the length is mostly earned, though it could be tighter for prompt economy.

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?

No output schema exists, yet the description fully explains return values (formatted text vs base64 image), all three params, content-type handling, and edge cases. Nothing an agent needs to invoke this correctly 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 coverage is 0%, so the description carries the full burden and does so thoroughly: enumerates all 8 output_format enum values with their exact renderings, explains case-insensitivity and the table-only applicability, documents include_schema's inferred types and default, and clarifies selection semantics including the cross-platform error.

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+resource ('Paste clipboard contents') and explicitly self-identifies as 'the primary clipboard tool', which differentiates it from siblings like clipboard_read_raw. An agent can select it confidently without opening another 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?

Exceptional. It enumerates trigger phrases, defines the counterintuitive case (referenced-but-missing data → check clipboard first), gives an explicit directive ('Do NOT ask the user to paste'), and distinguishes itself as the default over clipboard_read_raw.

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 cover safety (readOnly, idempotent, non-destructive), and the description adds substantial behavioral context beyond them: which MIME prefixes are accepted vs. blocked (image/, audio/, video/, application/octet-stream), that binary is rejected, that content is returned unparsed, and that 'primary' errors on macOS/Windows.

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 purpose and routing, then cleanly structured Args/Returns. Every sentence is useful, though the common MIME values are effectively stated twice (prose and Args), a minor redundancy.

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 a rich output schema and full annotations, the description still covers the gaps that matter: accepted/rejected MIME types, error conditions, and platform constraints. Nothing an agent needs to invoke it correctly 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 coverage is 0%, so the description carries full burden and does so thoroughly: it names common mime_type values, explains the text/* vs image/svg+xml vs application/* distinction, and documents the selection parameter's default and platform-specific 'primary' behavior.

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 ('Read raw clipboard content in a specific MIME format') and immediately positions itself against the sibling 'clipboard_paste' as a diagnostic-only tool. An agent can distinguish it from clipboard_paste without opening any 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?

Explicit routing guidance: use clipboard_paste for normal access, clipboard_list_formats first to discover MIME types, and clipboard_paste for images. It states both when to use this tool and when to prefer alternatives, with the conditions spelled out.

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 destructiveHint=false. The description adds useful behavioral detail beyond them: the version is read from package metadata at runtime, always matches the serving wheel, and falls back to '0.0.0+dev' if metadata is unavailable.

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 front-loaded with the core purpose, followed by usage contexts and return details. Every sentence earns its place by clarifying when to call it or what the fallback behavior is.

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, parameterless version tool with no destructive behavior, the description is complete: it explains the purpose, when to use it, the return shape, and the fallback case. The output schema exists, but the description's extra return detail is helpful rather than redundant.

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, so there are no parameter semantics to document. The baseline score for a parameterless tool is 4, and the description does not need to compensate for any schema 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?

The description states a specific verb and resource: 'Return the version of mcp-clipboard currently running.' It is immediately distinguishable from the clipboard-content siblings (paste, copy, read_raw, list_formats, etc.) because it reports package metadata rather than clipboard data.

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 gives clear usage contexts: test harnesses, diagnostic dumps, or when the user asks which version is installed. It does not explicitly state when not to use it or name alternatives, but the context is clear and actionable.

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