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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The word '확인' (check) plus the conditional about session expiry strongly indicate a non-mutating status check. The mention of needing to re-run login_setup.py on expiry adds useful operational context beyond a bare 'check session' statement.

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 two short sentences: one states the core action, the other provides the actionable follow-up for the failure condition. Every sentence earns its place, with no filler or tautology.

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 zero parameters, low complexity, and the presence of an output schema, the description does not need to document return values. It covers the tool's purpose and the single important post-condition (re-run login_setup.py on expiry), making it complete for an agent to invoke and interpret.

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 schema description coverage is 100%, so there is no parameter ambiguity for the description to resolve. This matches the baseline for a 0-parameter 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?

The description states a specific action and resource: 'check if session is alive' (세션이 살아있는지 확인). This clearly distinguishes it from the sibling content-management tools, all of which operate on categories, drafts, posts, or publishing. There is no ambiguity about what the tool does.

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 implies a use case: verify session liveness, and provides a concrete follow-up action if the session is expired: re-run login_setup.py. However, it does not explicitly state when to prefer this tool over alternatives or when not to use it, leaving some inference to the agent.

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 so richly: it discloses non-publishing behavior, supported Markdown formats, image/file attachment syntax, local-path-only restriction, 10MB file limit, formula/place syntax, and that place picks the first search result and reports it in the output.

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 statement is front-loaded and every included detail (formats, path rules, limit, place behavior) is useful. It is dense but not bloated.

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, return values need no explanation. The description covers the tool's non-trivial input conventions and place-selection behavior; minor gaps such as title/category handling and session requirements are not critical for correct invocation.

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 has 0% parameter descriptions, so the description must compensate. It thoroughly explains the markdown parameter's syntax and supported formats, but provides nothing about title, category, or tags beyond what their names/schema already imply.

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: writes a post in Markdown and saves it as a draft, and explicitly distinguishes itself by noting it does not publish. This clearly separates it from siblings like publish_draft.

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 context: use this to create and temporarily save a draft, not to publish. It does not explicitly name sibling alternatives or exclusion conditions, but the '발행하지 않는다' statement makes the tool's placement among draft/publish siblings clear.

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 succeeds. It discloses that deletion is unrecoverable, that confirm=True is mandatory, that partial title matches are allowed, that multiple matches are rejected, and that an empty title only works when exactly one draft exists. These are non-obvious, safety-critical behaviors.

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 compact sentences with no filler. The first front-loads the destructive action and mandatory confirmation; the second packs the title-matching rules efficiently. Every sentence earns 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?

The description is complete for a destructive tool with two parameters and an output schema. It covers irreversibility, confirmation, and title disambiguation. The reference to publish_draft for title rules is acceptable because that sibling tool provides the shared semantics.

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 must compensate. It fully documents both parameters: confirm must be true because the operation is irreversible, and title follows specific matching rules (partial match, multiple-match rejection, empty-title single-draft restriction). This goes well beyond the bare 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 and resource: 'Deletes the draft post' (임시저장 글을 삭제한다), which clearly identifies the tool's action. The draft resource naturally distinguishes it from delete_post, but it does not explicitly name a sibling to differentiate from, so it stops short of a 5.

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?

Provides no guidance about when to choose delete_draft over alternatives such as delete_post or publish_draft. The title rule reference to publish_draft is behavioral context, not usage guidance. The agent must infer when this tool is appropriate from the name alone.

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 burden and discloses critical behavior: deletion is irreversible, confirm=True is mandatory, and lookup by title is not supported. It could add auth or error behavior, but the safety-critical information is present.

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?

Concise and front-loaded: the core action, irreversibility, and confirm requirement appear first, followed by relevant sibling differentiation and target-specification guidance. 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 destructive tool with no annotations, this covers the essential points: target type, irreversibility, confirmation, and distinction from delete_draft. Minor gaps include failure behavior and session/auth prerequisites, but the output schema exists and return-value explanation is not required.

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%, but the description compensates by explaining url_or_log_no as the post URL or log number and clarifying that confirm=True must be set even though the schema defaults it to false. Both parameters receive meaningful semantic context.

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 action and resource: deletes a published post. Explicitly distinguishes itself from delete_draft, making the target resource and scope clear.

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?

Clearly differentiates this tool from delete_draft and instructs the agent to pass a URL or log number rather than a title. It stops short of explicitly stating 'use delete_draft for drafts,' but the distinction is strongly implied.

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 burden of behavior disclosure. It explains that the tool opens the publishing-settings layer, reads it, closes it, and does not publish. It also discloses that subcategories are shown with indentation, adding useful behavioral context beyond the tool name.

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 three short sentences with no filler. The main purpose is front-loaded, and each additional sentence contributes meaningful behavioral detail about side effects and output formatting.

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 zero-parameter listing tool with an output schema, the description is complete: it identifies the resource, confirms no publishing side effect, and explains the indentation behavior. Nothing critical is missing for an agent to call 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 has zero parameters and schema description coverage is 100%, so there are no parameter semantics to document. The baseline for a zero-parameter tool is 4, and the description does not need to add parameter detail.

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: it 'retrieves the blog category list.' It also explicitly says 'does not publish,' distinguishing it from the sibling publish_draft and clarifying that this is a read-only listing 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?

The description clearly implies use when the agent needs the blog's category list and explicitly rules out publishing behavior. It does not name an alternative tool, but the sibling set makes the purpose sufficiently distinct.

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?

No annotations are provided, so the description carries the behavioral burden. It does disclose that this is a read-style lookup ('조회한다') and specifies ordering ('최신순'), but it does not mention auth requirements, scope of drafts, pagination, or potential empty results.

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 extremely concise: a single sentence stating the action and ordering. It is front-loaded with the core purpose and contains no filler or redundant explanation.

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 zero-parameter list tool with an output schema, the description is nearly complete. It provides the resource, the action, and the ordering. It could add session or ownership context, but this is not essential for correctly invoking the tool.

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 no parameters, so the baseline is 4. The description correctly provides no parameter-specific details, and nothing further is needed for an agent to form arguments.

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 operation: retrieve the list of temporary-saved posts, sorted by latest. It is distinct from siblings like create_draft, delete_draft, and publish_draft, and from list_categories by resource, though it does not explicitly name an alternative.

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 this tool when the agent needs the list of drafts, especially in latest-first order. There is no explicit when-to-use or when-not-to-use guidance, nor mention of alternatives, but the operation itself makes the intended context reasonably clear.

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 behavioral burden and does so thoroughly. It discloses the mandatory confirmation flag, the rejection of ambiguous title matches, the restriction to exactly one draft when title is empty, the difficulty of undoing publication, and the visibility default behavior. These are meaningful behavioral traits beyond just 'publishes a draft'.

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 compact and front-loaded, leading with the primary action and the mandatory confirm flag. Every subsequent sentence adds essential edge-case or parameter context without redundancy or 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?

Given the tool's complexity and the absence of annotations, the description covers all three parameters, the confirmation requirement, ambiguity handling, irreversibility, and default visibility. Since an output schema exists, return-value documentation is not the description's burden; nothing critical is missing 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?

Schema description coverage is 0%, so the description must supply all parameter meaning. It fully explains title matching semantics, the confirm requirement, and the allowed visibility values and their default behavior. This more than compensates for the empty schema descriptions.

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 core action: loading a saved draft and publishing it. It distinguishes itself from sibling tools like create_draft, list_drafts, and delete_draft by focusing on the publish workflow, and adds the critical precondition that confirm=True is required.

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 strong usage context: drafts are not auto-restored, so the user must explicitly select one from a list first. It also explains the conditions under which publication will proceed (unique title match, or exactly one draft when title is empty). However, it does not explicitly name sibling tools as alternatives, leaving some routing implicit.

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