Docs MD — Markdown Share

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly declares permanence (implying irreversibility) and requires an edit token, which signals authorization and helps predict that unauthorized deletions will fail. This covers key safety aspects, though error handling and side effects are not discussed.

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 sentence with no redundant words. It front-loads the primary action ('Permanently delete') and immediately specifies the required identifiers, making it highly efficient 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 simple delete operation with complete schema coverage and no output schema, the description adequately covers the action, required inputs, and important context (permanence, token). No additional return-value explanation is needed. The information provided is sufficient for an agent to invoke this tool correctly.

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 input schema already provides 100% description coverage, fully explaining both 'id' as the URL path segment and 'edit_token' as the token from creation. The description merely restates these parameter names without adding new meaning, so the baseline score 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 clearly states the tool's purpose with a specific verb ('delete'), a resource ('share'), and a critical qualifier ('permanently'), making it easy to distinguish from siblings that create or update shares. The scope is unambiguous and leaves no doubt about the operation.

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: use when you need to permanently delete a share. However, the description does not explicitly state when to use this tool over alternatives (e.g., 'instead of update_share') or mention any prerequisites beyond requiring the id and edit token. The guidance is functional but minimal.

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 safety profile is covered. The description adds that it accepts either a share id or any share URL and that the result is raw markdown, which is useful. It does not mention error behavior for invalid links or auth requirements, so it adds only modest context.

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 tight sentences with the core action front-loaded and the usage trigger second. Zero 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 one-parameter read tool with annotations covering safety and no output schema, the description adequately covers what it returns (raw markdown) and how to invoke it. Only a note on failure modes for invalid shares 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 100% and the single parameter's description already documents both accepted forms (share id or URL). The description restates the same flexible-input behavior without adding format examples or constraints, 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?

States a specific verb and resource: 'Fetch the raw markdown of a docs-md.com share.' Clear what it does, but it does not distinguish itself from the sibling 'share_markdown', which an agent could easily confuse on name alone.

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 concrete trigger: 'Use it when someone gives you a docs-md.com link, for example a handoff written by another agent.' No explicit when-not or direct alternative named, but the usage 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.

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

With no annotations, the description carries the full burden and does well: it discloses the key side effect (content becomes public), what is returned (rendered URL, raw-markdown URL, edit token), and that the token is needed for later updates or deletion. It omits auth requirements and whether publishing is reversible via that token beyond a passing mention.

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 tight sentences, front-loaded with the core action and followed by usage and return values. Every sentence earns its place with no 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?

There is no output schema, so the description's decision to enumerate the return values (URL, raw-markdown URL, edit token) fills exactly the gap an agent would otherwise have. Combined with the schema covering the inputs, nothing needed to call the tool 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 100%, so expiry, content, and filename are already fully documented in the schema (including the enum values and the 120,000-character limit). The description adds no parameter-level meaning 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 uses a specific verb and resource ('Publish markdown at a public docs-md.com link') and even describes the rendering capability. It is clearly the creation tool among the sibling set (read_share, update_share, delete_share), though it never names those siblings explicitly to draw the contrast.

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 states concrete use cases ('send a plan, spec, report, README or agent handoff to a person or another agent'), which gives an agent a clear trigger. It stops short of naming alternatives or exclusions, so an agent must infer that updating an existing link belongs to update_share.

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?

With no annotations provided, the description carries the full burden of disclosing behavior. It explicitly states the destructive action ('Replace the content') and the auth requirement ('using its id and edit token'), covering the two most critical behavioral traits. However, it does not mention side effects on other fields like filename or whether the operation is reversible, which prevents a higher score.

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, front-loaded sentence with the action verb 'Replace' at the start. There is no wasted or redundant wording; every word contributes to the meaning. This is an exemplar of conciseness.

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?

The tool has 4 parameters, no output schema, and no annotations, so the description must compensate for the lack of structure. It clearly explains the core action and auth requirement, but leaves ambiguity about the optional filename behavior (e.g., whether filename changes require content replacement) and does not describe the return value or potential errors. This is adequate for a simple update tool but not fully 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?

The input schema has 100% parameter description coverage, so the description adds little beyond what the schema already provides. It reinforces the roles of id and edit_token for identifying the share, but does not clarify any additional semantics (e.g., how filename interacts with content replacement). The schema already carries the parameter details, so the 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 uses the specific verb 'Replace' and clearly identifies the resource as 'the content of an existing share,' which distinguishes it from the sibling tools share_markdown (create) and delete_share (delete). The mention of 'existing share' reinforces that this is an update operation, making the purpose unambiguous.

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 provides clear context that this tool is for modifying an existing share, not for creating or deleting shares. However, it does not explicitly name alternatives or state when not to use it, so it stops short of full usage guidelines. The sibling tool names are inferable but not referenced.

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