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

No annotations are provided, so the description carries the full burden, and it discloses almost nothing: it does not state whether deletion is permanent or recoverable, what happens to unmatched filters, or any auth/rate-limit constraints. '(use with caution)' gestures at destructiveness but conveys no concrete behavioral trait.

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 short sentence that front-loads the action and resource with no filler. The parenthetical earns marginal value, so it is efficient though not maximally informative.

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?

This is a destructive bulk mutation with no annotations and no output schema, yet the description omits irreversibility, filter semantics, partial-failure behavior, and return information. For a high-blast-radius tool, the definition is materially under-specified.

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% for both parameters, so the schema already documents that filter selects posts and confirm must be true. The description adds no syntax, format, or filter-expression detail beyond that, which is the baseline 3 when the schema does the heavy lifting.

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 (bulk delete posts) and the word 'bulk' implicitly distinguishes it from the single-item sibling ghost_posts_delete. However, it never names the single-delete alternative, so the differentiation is left to inference rather than explicit.

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 only guidance is the parenthetical '(use with caution)', which is a warning rather than a when-to-use rule. It does not say when to prefer bulk_delete over ghost_posts_delete for a single post, nor what prerequisites (permissions, filter scope) apply.

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 for a mutation tool. It omits critical traits: whether updates merge or replace fields (e.g., does 'tags' append or overwrite?), what happens to non-matching posts, partial-failure behavior, and permission requirements.

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 four-word phrase is maximally concise and front-loaded, but it is under-specified rather than efficient; nothing beyond the title is communicated. Brevity here comes at the cost of usefulness.

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 bulk mutation with a nested object parameter, no annotations, and no output schema, the description should cover merge semantics, failure behavior, and result reporting. None of that is present, leaving significant gaps an agent needs to call it safely.

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%, with both 'data' and 'filter' documented including a filter syntax example ('status:draft'), so the baseline is 3. The description adds no meaning beyond the schema — it never mentions the filter-based selection model or which fields 'data' accepts.

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 with the 'bulk' scope qualifier, which distinguishes it from the single-record sibling ghost_posts_update. It does not, however, say which fields can be updated or how posts are selected, so the differentiation is scope-only.

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?

No when-to-use guidance, no prerequisites, and no reference to alternatives such as ghost_posts_update (single) or ghost_posts_bulk_delete. The agent must infer that 'bulk' means many posts matched by the filter, which the description never states.

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 discloses essentially nothing: no auth/permission requirements, no mention that title is required despite the schema marking zero required params, no side effects, and no clarification of the create-vs-publish relationship. Only the mutation nature is inferable from the verb.

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 single sentence is front-loaded and waste-free, which is structurally fine, but for a 23-parameter creation tool it is under-specified rather than genuinely concise.

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?

A 23-parameter write tool with no annotations and no output schema needs far more than four words. Nothing about required fields, defaults, publishing behavior, or the returned resource is conveyed, leaving the agent to reconstruct intent from the schema alone.

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 all 23 parameters are already documented in the schema (defaults, formats, enums). The description adds no parameter meaning beyond that, 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 states a clear verb+resource ('Create a new post'), which is unambiguous about what the tool does. It does not, however, differentiate this tool from siblings like ghost_posts_publish or ghost_posts_update, nor explain how creation interacts with the publish lifecycle.

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 guidance on when to use this tool versus alternatives, despite a dense sibling set (publish, unpublish, update, bulk_update). The agent gets no signal about whether creating with status='published' is preferred over create-then-publish.

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. 'Permanently' is a genuine behavioral disclosure of irreversibility, which is the most important trait here. However, it omits authorization requirements, error behavior for nonexistent IDs, and whether deletion cascades.

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 four-word sentence that front-loads the verb and resource and includes only the one qualifier that matters. No waste.

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, no-output-schema delete tool, the description covers the essential fact (irreversibility). It could be stronger by routing the agent to bulk_delete for multi-post cases, but nothing critical 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 100% for the single 'id' parameter, so the schema already documents the argument fully. The description adds no format, prefix, or lookup detail beyond what the schema states, which is the baseline 3 case.

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 ('Delete') and resource ('a post'), and the qualifier 'permanently' signals this is not a soft delete. It is clearly separable from ghost_posts_get/list/create/update, though it never explicitly contrasts with the sibling ghost_posts_bulk_delete.

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?

No guidance on when to use this versus ghost_posts_bulk_delete or ghost_posts_unpublish. The agent must infer from names alone that this is the single-post irreversible path.

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. It does not disclose that this is a read-only lookup, what happens if both id and slug are omitted (0 required params), or whether a missing post errors or returns null.

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 leaves required behavioral detail unstated rather than being a model of concision.

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 read tool with fully documented parameters this is close to adequate, but with no annotations and no output schema, the description should at minimum say what is returned or how missing posts are handled.

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 all five parameters (id, slug, fields, formats, include) are already documented in the schema with examples. The description adds nothing beyond the schema, so baseline 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 ('Get a single post') and narrows the lookup key to ID or slug, which distinguishes it from ghost_posts_list and ghost_posts_search. It does not explicitly name those siblings, so it falls 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?

There is no guidance on when to use this instead of ghost_posts_list or ghost_posts_search, nor any note about behavior when neither id nor slug resolves. Usage is only implied by the name and description.

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 supplied, so the description carries the full behavioral burden, yet it only states 'Returns posts with metadata.' It omits pagination semantics, default ordering, how the filter/fields/include strings combine, and whether this is a safe read. 'Returns posts with metadata' is too thin for a 7-parameter listing tool with zero 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?

Two short, front-loaded sentences with no padding; the verb and scope come first. It is efficient, though it is arguably terse rather than rightly sized for a 7-parameter 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?

With no annotations, no output schema, seven parameters, and nine siblings including a near-duplicate search tool, the description should clarify list-vs-search behavior and return shape. As written, key selection and invocation context 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 100% and every parameter has an example-bearing description (order, fields, filter, include, formats), so the schema already does the heavy lifting. The description adds only 'optional filters,' which restates rather than extends the schema, making the baseline 3 correct.

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 clear verb+resource ('List posts') and notes optional filtering, which is enough to identify the operation. However, it never distinguishes itself from the sibling ghost_posts_search, which overlaps heavily with listing plus filtering, so the agent must guess which to pick.

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 phrase 'with optional filters' implies a use case but gives no when-to-use, prerequisites, or guidance on choosing between this and ghost_posts_search or the bulk siblings. No exclusions or alternative routing are provided.

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. It omits that publishing is a state-changing, likely irreversible action, that it may email subscribers by default, and what preconditions apply. For a mutation tool with zero annotation coverage this is a meaningful 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, but it is arguably under-specified rather than genuinely concise given the tool's side effects.

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 four parameters controlling an irreversible publish plus email dispatch, the description is too thin to let an agent invoke it confidently. Key behavioral context about side effects and preconditions 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 100%, so the schema already documents all four parameters including the send_email default and published_at behavior. The description adds nothing beyond that, which is the baseline expectation when the schema does the heavy lifting.

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 (publish) and resource (draft post), and the inverse sibling ghost_posts_unpublish makes the scope reasonably clear. It doesn't explicitly contrast with siblings like ghost_posts_update, but the action is 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?

No guidance on when to use this versus ghost_posts_update or ghost_posts_unpublish, no prerequisites (e.g., post must be a draft), and no mention of the subscriber-email side effect that would affect a caller's decision.

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, and it discloses almost nothing. It does not state that this is a read-only operation, whether results are paginated, how 'include' changes the response shape, or what the limit default is.

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 short sentence with the key noun front-loaded and no filler. It is efficient, though its brevity edges toward under-specification rather than true 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?

For a three-parameter read tool with full schema coverage and no output schema, the description is minimally viable but leaves behavioral questions open. An agent can call it, but cannot predict pagination, result shape, or the effect of 'include'.

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 all three parameters are already documented in the schema and the baseline is 3. The description adds only 'by query string', which restates the query parameter without new syntax or format 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?

States a specific verb ('Search') plus resource ('posts') and the mechanism ('by query string'), which is enough for an agent to distinguish it from ghost_posts_get or ghost_posts_create. It never explicitly contrasts with ghost_posts_list, the closest sibling, so differentiation is inferred rather than stated.

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?

No guidance on when to use search versus ghost_posts_list, no prerequisites, no note on whether query is required despite the schema marking it so. The agent must infer the selection condition from the tool 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?

No annotations are provided, so the description carries the full behavioral burden. It states the mutation (published -> draft) but omits whether the change is reversible, what permissions are required, and any side effects such as breaking live URLs or losing scheduled state.

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 filler; the core action and its effect are stated 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 one-parameter state-change tool with no output schema, the essential action is conveyed, but the absence of annotations means the description should say more about permissions, reversibility, and side effects. It is adequate but leaves real gaps for a mutation operation.

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% for the single 'id' parameter, so the schema already documents its meaning and required-ness. The description adds nothing beyond that, which matches the baseline 3 when the schema does the heavy lifting.

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 (unpublish) and resource (post), and the parenthetical '(convert to draft)' disambiguates the exact semantic effect. An agent can distinguish this from the sibling ghost_posts_publish without opening 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?

There is no explicit when-to-use guidance, no prerequisites, and no mention of the alternative (ghost_posts_publish) or of what happens if the post is already a draft. Usage must be inferred from the word 'published'.

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 behavioral burden and discloses almost nothing: it does not state that partial updates are allowed, that tags/authors replace existing arrays, that updates may affect publication state, or what permissions are required. The only hint of behavior ('existing') is a restatement of the mutation semantics.

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?

It is a single front-loaded sentence with no waste, but for a 15-parameter mutation tool this level of brevity is under-specification rather than genuine 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?

Given 15 parameters, zero annotations, no output schema, and a dense sibling set, the description is far too thin to be complete. It leaves update semantics, permissions, and differentiation from bulk/publish variants entirely unaddressed.

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% and each of the 15 parameters is individually documented (including enum values and 'replaces existing' semantics), so the schema does the heavy lifting. The description adds no meaning beyond the schema, which is the baseline-3 case.

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 verb+resource ('Update an existing post') is clear, but it does nothing to distinguish this tool from siblings like ghost_posts_bulk_update, ghost_posts_publish, or ghost_posts_unpublish, which are all mutations of the same resource. An agent cannot tell from the description which mutation path applies.

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?

No when-to-use guidance, no exclusions, and no reference to the many sibling mutation tools (bulk_update, publish, unpublish). The agent must infer that this is the single-post edit path entirely from the name.

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