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

No annotations are provided, so the description carries the full burden. It usefully discloses that created content is a private draft (not published) and that a confirm gate guards the write, which is meaningful behavioral context. It omits auth requirements, what preview returns, and behavior on slug conflicts, so disclosure remains incomplete for a mutating tool.

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, front-loaded sentences with zero filler. The purpose leads and the gating constraint follows immediately.

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 5-parameter mutation tool with no annotations, no output schema, and 0% schema description coverage, the description is too thin. It doesn't clarify urlSlug/tags semantics, preview return shape, or failure modes, so an agent cannot call it with full confidence.

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% across 5 parameters. The description explains only 'confirm' (must be true for writing); title and body are self-evident, but tags and especially urlSlug receive no semantic explanation anywhere, leaving notable gaps.

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 ('create a private Velog draft') and disambiguates draft from published content via 'private'. It does not explicitly name velog_publish_post as the publish alternative, but the draft/private framing implicitly differentiates it from the publish sibling.

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 sentence 'Writing requires confirm=true' gives a concrete gating condition for when actual creation occurs, and 'Preview or create' implies confirm=false yields a preview. However, it never states when to use this vs. velog_publish_post or how preview output differs, leaving usage coverage partial.

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 exist, so the description carries the full behavioral burden. It usefully discloses the no-network trait, but for a tool that writes files to disk it says nothing about where files land, whether existing files are overwritten, or how errors surface — the details an agent most needs before invoking a filesystem mutation.

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 tight sentence with the key scoping constraints (local index, no network) front-loaded. Every clause earns its place and nothing is wasted.

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 no annotations, no output schema, and zero parameter documentation, the description is too thin for an export tool. An agent cannot determine the destination of the exported Markdown, the meaning of 'username', or whether a prior sync is required before calling 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 description coverage is 0%, and the single parameter 'username' is never mentioned in the description. The one input that determines whose posts get exported is left entirely unexplained, with no indication of whether it is a blog identifier, an account name, or what happens with an unknown user.

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 (Export) and resource (posts already synced into the local index) with the output form (Markdown files). The phrase 'already synced into the local index' implicitly separates it from network-facing siblings like velog_list_posts and velog_get_post, though no sibling is named explicitly.

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 'without making a network request' clause implies when this tool is preferable to network-backed siblings, and 'already synced' hints that velog_sync_local_index must run first. However, neither the prerequisite nor the alternative tools are named, so the routing guidance is only 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, the description carries the full burden. 'Audit' implies a read-only check, but it never states whether the body is modified, whether findings block a save, what severity levels exist, or what the response looks like. For a validation tool invoked before a write, the absence of any statement about mutability or output is a real gap.

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 front-loaded sentence with no filler, and the three audit dimensions are enumerated compactly. It is efficient, though the brevity is part of why other dimensions are underspecified.

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 annotations, no output schema, and 0% parameter documentation. The description should therefore explain what an audit returns and whether it alters input, and it does neither. An agent cannot tell what to do with the result or how it relates to the create/publish siblings.

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% for three parameters, and the description mentions none of them. 'Velog Markdown' loosely implies the body is the audited content, but title, tags, and their constraints (max lengths, tag limits) get no semantic treatment anywhere. The description does not compensate for the coverage 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 gives a specific verb ('Audit') and resource ('Velog Markdown') plus the three check categories (structure, accessibility, secret-like content). However, it conflicts with the tool name 'velog_format_markdown', which suggests reformatting rather than auditing — an agent reading the name may expect the content to be rewritten. That tension leaves the core purpose only partially resolved.

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?

'before saving' hints at a workflow position but names no alternative. Siblings like velog_create_draft and velog_publish_post are obvious candidates for a 'run this first, then call X' instruction, and none are referenced. No when-not conditions are given either.

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. It does disclose two useful behavioral facts: only public posts are readable (so drafts/private content is out of scope) and the response includes the Markdown body. It says nothing about behavior on missing/private posts, authentication requirements, or rate limits.

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 front-loaded sentence with no filler; the scope qualifier ('public') and the return content ('Markdown body') are packed in efficiently. Brevity borders on under-specification, but nothing written is wasted.

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-required-param tool with no annotations, no output schema, and 0% schema coverage, the description is too thin. An agent still lacks any explanation of the parameters or of failure modes, which the structured fields do not supply.

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% with two required parameters (username, urlSlug), so the description must compensate and does not. It never explains that username is the author handle and urlSlug is the post identifier, leaving both fields semantically undocumented.

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 concrete verb and resource: 'Read one public Velog post, including its Markdown body.' The word 'one' and 'public' implicitly separate it from velog_list_posts and velog_search_posts, but no sibling is named explicitly.

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 the tool for fetching a single known post by username/urlSlug rather than searching or listing. There is no explicit when-to-use, no when-not-to-use, and no pointer to alternatives such as velog_search_posts when the slug is unknown.

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 it discloses only that results are public posts. It says nothing about cursor-based pagination behavior, default result size, rate limits, or what the response includes, which are the key operational traits for a listing tool.

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 front-loaded sentence with zero waste, but the brevity reflects under-specification rather than discipline — the pagination and filtering mechanics an agent needs are absent.

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 4-parameter listing tool with no annotations and no output schema, the description leaves pagination, filtering, result shape, and limits entirely unaddressed. An agent could invoke it but cannot predict behavior or page through results 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% across 4 parameters, so the description must compensate but only covers 'username'. The tag filter, limit (default 20, max 50), and cursor pagination are completely unexplained in both the schema and the description.

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 gives a specific verb ('List') and resource ('public posts'), and scopes it to a single Velog username, which cleanly separates it from velog_get_post (single post) and velog_search_posts. It does not explicitly name those siblings, which keeps it below 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?

There is no statement of when to use this versus velog_search_posts, velog_search_local_index, or velog_get_post, and no prerequisites or exclusions. The agent must infer the choice 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 must carry the behavioral burden. It usefully discloses that posts are private and that confirm=true is a write gate, which is real value, but it omits what publishing actually does (irreversibility, whether a URL/slug is returned or reused), auth requirements, and rate limits.

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, front-loaded sentences with no filler. Brevity is a virtue here, though it shades into under-specification for a five-parameter mutation tool.

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 mutation tool with no annotations, no output schema, and zero schema descriptions on five parameters, the definition is too thin. It should at minimum explain urlSlug behavior, what preview returns, and what distinguishes this from the sibling draft 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?

Schema description coverage is 0% across five parameters, and the description only explains one of them (confirm). title, body, tags and especially urlSlug (unique? auto-generated? collision behavior?) get no semantic help from either the schema or the description.

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 pair (preview/publish) plus resource (a private Velog post), so the agent knows this is the posting tool rather than a formatting or listing one. It does not explicitly contrast itself with the sibling velog_create_draft, leaving the publish-vs-draft distinction to inference from the name.

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?

'Writing requires confirm=true' implies a preview-first flow and tells the agent one gating condition. It never states when to call this instead of velog_create_draft, nor whether confirm=true can be set on the first call or whether a preview must precede it.

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 full behavioral burden. It discloses the sync dependency but says nothing about matching semantics (keyword vs substring), read-only safety, behavior on an empty or stale index, or result ordering — all material for a search tool.

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 front-loaded sentence with no filler. It is efficient, though the brevity reflects under-specification rather than disciplined trimming.

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?

Three parameters with zero descriptions, no annotations, and no output schema leave the agent without essentials: which user's index is searched, how many results return, and what happens if nothing has been synced. The single sentence is not enough for this complexity.

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% and all three parameters (username, query, limit) are bare typed fields. The description mentions neither the required username scoping nor the limit cap of 50, so it does not compensate for the 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?

States a specific verb (search) and a specific resource (posts in the local keyword index), and 'previously synced' scopes it away from a live API search. It stops short of naming velog_search_posts as the live counterpart, so an agent must infer the distinction.

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?

'Previously synced into the local keyword index' implies a prerequisite (content must have been synced first) and hints at the sync sibling, but there is no explicit when-to-use/when-not statement or named alternative such as velog_search_posts for live results.

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 full burden. 'Public' is a useful constraint implying no auth and no private content, but it says nothing about rate limits, pagination, result size (the schema caps limit at 50) or what a result contains.

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 front-loaded sentence with no filler. It is efficient, though its brevity edges toward under-specification rather than optimal density.

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 no annotations, no output schema, and 0% schema description coverage, the description should explain return shape and the limit parameter. It leaves nearly all behavioral and return-value context to inference.

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% for three parameters. The description implicitly covers 'query' (keyword) and 'username' (optionally one username), but never mentions 'limit' or its 1–50 range, so a third of the surface remains undocumented in prose and schema alike.

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 ('Search public Velog posts') plus the two scoping dimensions (keyword, username). The word 'public' implicitly distinguishes it from the sibling velog_search_local_index, 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?

'Optionally within one username' hints at the narrowing use case, but there is no explicit when-to-use/when-not guidance and no mention of the close alternative velog_search_local_index for local content. Usage is inferable 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?

No annotations exist, so the description carries the full burden. It does disclose meaningful behavior — scope is 'all public posts' and the effect is a write into the local keyword index — but it says nothing about rate limits, network dependence, whether the index is replaced or merged, or error handling.

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 sentence that front-loads the action and scope with zero filler. Nothing could be removed 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?

For a one-parameter tool with no annotations and no output schema, the description is minimally viable but leaves gaps: what the tool returns (count of indexed posts?), whether re-syncing duplicates or overwrites entries, and how failures surface are all unstated.

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 one required parameter at 0% schema description coverage, the description must compensate. It clarifies the parameter is a single Velog username, but gives no format guidance (e.g. '@' prefix, casing, URL slug vs handle) beyond the schema's length bounds.

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 (sync) and resource (all public posts for one Velog username) plus the destination (local keyword index), which separates it from read-only siblings like velog_list_posts and velog_search_posts. It does not explicitly contrast with velog_export_local_posts, so it stops short of full sibling differentiation.

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 the tool to run before velog_search_local_index, but the description never says so, nor does it state prerequisites or that only public posts are eligible. No exclusions or alternatives are named.

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