craft-content-mcp

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

Beyond the readOnly/openWorld/destructive annotations, the description discloses the actual payload (headline, story with each result, quote, social and email copy, sector notes) and the placeholder convention that a bracket marks anything not supplied. It also flags a compliance obligation around customer approval and intended use, which annotations cannot express. This is genuinely additive behavioral 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?

The opening sentence front-loads purpose and the mode split, and the return-contents list is efficient. The paragraph is dense and packs several distinct ideas (inputs, outputs, brackets, approval) into few sentences, which is appropriate for a 12-parameter tool, though a minor structural break would improve scanability.

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 output schema, the description carries the return-value burden and does so by enumerating output sections and the bracket placeholder rule. It also covers both modes and the approval prerequisite. It stops short of specifying output formatting or how sector notes are shaped, leaving a small residual 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 coverage is 100% and the per-parameter descriptions already explain mode gating, sector derivation with neutral fallback, and interview_notes backfilling, so the description largely restates structured data. It does add a compact summary of how industry, quote, notes and business model tune the wording, plus the bracket convention, but the marginal value is modest given the schema's 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 concrete verb and artifact: it turns a customer result into a case study, with two named modes (full builds the study, discovery produces an interview kit). It distinguishes the modes clearly enough that an agent can pick one, but it never names which sibling tool to prefer (e.g. testimonial_capture or sales_enablement_content) for adjacent needs.

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 conditions are stated: mode full requires challenge, solution and results, while discovery is the path when those are missing, and interview_notes backfill a gap in full mode. It also sets a precondition to confirm written customer approval for the exact material and use. What is absent is any exclusion versus neighboring content tools, so an agent gets context but no routing rules.

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?

Beyond the readOnly/openWorld/destructive annotations, the description discloses genuinely useful behavior: outputs are written from whole sentences of the source with key points preserved in source order, unsupported claims are traced back to the source, and unrecognized target formats are reported rather than fabricated. It also flags the approval requirement and that a draft cannot grant customer permission. This is rich disclosure the annotations could not supply.

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 definition is front-loaded with what it produces and what it needs, then layers in the grounding and format-handling rules. Every clause carries information, though the closing sentence about customer approval reads like a procedural instruction rather than a property of the tool, slightly blurring the description's focus.

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 output schema, the description correctly takes on the burden of describing return values and their provenance, which it does well. For a 7-parameter tool with four enums it is nearly complete, though it never mentions the optional sector parameter or how sector affects output, leaving that to the schema.

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 already 100%, so the bar is a baseline 3, but the description adds meaning: target_formats has a documented default set and unknown names are named instead of written, brand_voice and key_message are framed as steering levers, and publication_approval is tied to a before-publication check. It does not cover your_sector, leaving one parameter's intent to the schema alone.

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: it turns one piece of source content into versions for other channels, and it enumerates the output types (LinkedIn post, X thread, email, blog summary, quote cards). That is far more concrete than a restatement of the name. It does not explicitly differentiate itself from siblings like newsletter_builder or thought_leadership_series, which keeps it from 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?

It makes clear the entry condition (you have a single piece of content and want channel-specific versions) and names the required inputs plus the optional levers that steer output. It also introduces a prerequisite around customer approval before publication. There is no explicit when-not-to-use guidance or named alternative tool, so it falls short of a 5.

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 the safety profile (readOnlyHint, destructiveHint false, openWorldHint false), so the bar is lower, and the description still adds real behavior: it enumerates the scored areas, notes that each deduction is quoted from the text, and discloses the edge case that nothing-to-edit yields no improved version. It stops short of describing the score scale or output shape, which keeps it from a 5.

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 purpose and the return behavior are front-loaded, and the closing sentence covers the meaningful empty-result case rather than padding. The parenthetical list of scored areas is long but each item is informative, so little 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 output schema, the description carries the burden of explaining returns and does so: per-area scores, quoted deductions, and the edits made, plus the no-op behavior. What remains unstated is the scoring scale and whether the improved version is returned alongside the report, which an agent might want before calling.

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 six parameters including the three enums are already well documented in the schema itself. The description only restates that goal, audience and tone preference 'refine the review,' adding no syntax or interpretation guidance beyond that baseline.

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 opens with a specific verb and resource: it reviews a draft and tells you 'whether a draft is ready to publish and what to fix first,' driven by 'the pasted copy and its content type.' That is clearly distinct from the generator-oriented siblings (case_study_generator, newsletter_builder, webinar_script), though it never names a sibling to route away from.

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 by the phrase 'decide whether a draft is ready to publish,' which suggests a pre-publish review gate, and the optional goal/audience/tone parameters are framed as refinements. There is no explicit statement of when NOT to use it, no mention of alternatives among the sibling tools, and no prerequisite context.

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 mark this as a safe read-only, closed-world operation, and the description adds substantial behavior beyond that: the exact shape of the returned draft (subject line and preview, opening, per-key-point sections, CTA button, A/B subject lines, alternate hooks, sector notes). It also discloses a meaningful limitation — it adds no statistic or customer story and reports what it did not receive — which tells the agent how to handle thin inputs and what to verify before publishing.

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 dense but front-loaded, leading with what the tool decides and who it is for before listing the returned artifact. Nearly every clause carries information, though the final sentence about asking whether written customer approval covers the material is vague about who is asking and of whom, which weakens the close.

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 ten-parameter generation tool with no output schema, the description covers inputs, the full return structure and a publication-safety caveat, so an agent can call it and interpret the result correctly. Minor gaps remain around draft length, language, and whether output is persisted anywhere, but nothing essential to invocation 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 five parameters carry enums, so the schema already explains tone, sector, newsletter type, audience and approval states. The description's prose restates the same optional inputs (key points, audience segment, newsletter type, tone, earlier topics, product) without adding syntax, defaults or interactions the schema does not already convey. Baseline 3 is appropriate 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 names a specific resource and deliverable: it decides what goes into a newsletter issue and which subject line to test, and returns a full draft. It is clearly a newsletter-drafting tool rather than a general rewriter, which separates it from content_repurposer or craft_content_improver. It stops short of naming any sibling explicitly, so differentiation is inferred from the newsletter framing.

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 the inputs that drive the tool (your topic and the action you want readers to take) and adds a real usage caveat about confirming written customer approval for names, figures, quotes and intended use. It gives no explicit exclusions or 'use X instead when...' routing against the other seven content-generation siblings, so the agent must infer boundaries.

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 establish readOnly=true, destructive=false and closed-world, so the safety profile is covered. The description goes beyond that by disclosing inference and fallback behavior: value props are derived from proof points when omitted, sector is inferred and stays neutral when unclear, and objections are suggested from the sector when not supplied. It also summarizes the returned sections, which matters because there is no output schema.

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 front-loaded with the purpose, then inputs, then returns, then the no-objections fallback, and every sentence carries information. The input enumeration sentence is the one mildly redundant part given the 100%-documented schema.

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 10-parameter tool with no output schema, the description covers purpose, key inputs, conditional inference and the shape of the output, which is what an agent needs to call it correctly. The main residual gap is that it never positions the tool against its many content 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 100% and the schema already spells out optionality, enums and inference for your_sector and business_model. The description's enumeration of shaping inputs ('Optional objections, value propositions, competitor objections, price context, sales stage and business model') largely restates the schema rather than adding format or precedence detail, so the 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?

The description states a concrete outcome: deciding what sellers should say at each deal stage, driven by product, persona and proof points, and it names the artifacts produced (pitch order, objection answers, competitor responses, discovery questions, follow-up templates). That is specific enough to distinguish it from content-generation siblings like webinar_script or case_study_generator, but it never explicitly contrasts itself with them.

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 by the phrasing 'at each stage of a deal' and by the sales_stage enum, and there is useful conditional guidance ('Without objections it suggests the ones your sector raises'). However, there is no explicit when-to-use/when-not guidance and no routing to or away from the sibling tools.

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, destructiveHint=false and closed-world scope, and the description does not contradict them. It adds real behavioral substance beyond that: it enumerates the four returned artifacts (request email, role/sector interview questions, editable quote drafts, sign-off checklist), states the fallback behavior when no product name is supplied, and flags the customer-approval prerequisite.

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 first sentence front-loads purpose and required inputs, followed by optional inputs, then outputs, then the approval caveat – a sensible order. A small amount of redundancy exists, notably the product-name sentence that restates the your_product schema description, but no sentence is 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?

With 13 parameters, 4 required, and no output schema, the description takes on the burden of explaining return values and does so explicitly with its four artifacts. It also covers the notable edge behavior (missing product name) and the approval/compliance requirement, which is the main risk surface for a testimonial workflow.

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 carries the parameter documentation and the baseline is 3. The description's summary ("optional role, relationship, intended use, incentive, your product and business model") groups optional inputs loosely and repeats the product-name behavior already written in the schema, adding little new semantics.

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?

"Helps you ask a happy customer for a testimonial" states a specific verb and resource, then names the exact inputs (name, company, success story, testimonial type) that drive it. It is clear what the tool produces, but it never contrasts itself with siblings like case_study_generator or sales_enablement_content, leaving an agent to infer the boundary.

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 context is implied by the opening clause and reinforced by the closing instruction to check that approval covers the exact material and intended use. However, there is no explicit when-to-use/when-not-to-use framing and no named alternative for adjacent needs such as full case studies, so the routing guidance stays implicit.

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?

Beyond readOnlyHint/openWorldHint/destructiveHint, the description discloses the full return shape (headline, first draft, objection, proof, test, promo post, publishing order, sector notes), a non-fabrication guarantee ('no result, customer or figure is invented'), and a real constraint about customer approval scope. That is unusually rich behavioral context that annotations alone would never convey.

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, then outputs, then guarantees, with no filler sentences. Slightly dense and one clause ('Ask whether written customer approval...') reads as an instruction packed into the description, but overall it earns its length.

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, and the description compensates by enumerating exactly what each article returns. For a 9-parameter generation tool the only meaningful gap is the absence of explicit sibling differentiation, which is a routing concern rather than a calling concern.

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 every parameter is already documented, and the description largely restates them ('optional proof points, author background, number of articles and article style'). It adds little syntax or default semantics 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: it decides what to publish to make a point of view known, then produces article series. An agent can tell this apart from case_study_generator or testimonial_capture by the 'build authority through articles' framing. It does not explicitly name a sibling alternative, 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?

Usage is implied through 'from your topic, your take and the reader you write for' and the publishing-context framing, but there is no explicit when-to-use, when-not-to-use, or named alternative among the seven content siblings. The approval instruction is a workflow step, not tool-selection guidance.

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 the safety profile (readOnlyHint true, destructiveHint false, openWorldHint false), and the description adds genuinely new behavior: an input-grounding guarantee ('uses only what you gave and says what it did not get') and a compliance caveat that a draft cannot grant customer permission. What it does not say is anything about latency, determinism across repeated calls, or limits on input size.

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?

Four sentences, front-loaded with the purpose, then optional inputs, then outputs, then the compliance caveat. The input list and output list are dense but each earns its place by telling the agent what will and will not be returned. The final imperative is slightly abrupt in placement but carries real content.

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 12 parameters and no output schema, the description carries the burden of explaining returns, and it does so in detail: run of show, spoken script with speaker lines and on-screen cues, polls, likely Q&A, follow-up email sequence, sector notes. It also flags the customer-approval prerequisite. Complete enough for correct invocation, missing only sibling comparison.

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 every one of the 12 parameters, including the six enums, is already documented in the schema, and the fallback behavior for omitted values is described there too. The description's enumeration of optional shaping inputs largely restates parameter names rather than adding new semantics. Baseline 3 is the right ceiling here.

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 opens with a specific verb-plus-resource: plan a webinar that leads to meetings, driven by topic, target audience and webinar type. That is concrete enough to separate it from siblings such as newsletter_builder or case_study_generator, although it never names a sibling or states the boundary explicitly, which keeps it 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?

Usage is implied by the stated goal (a webinar whose purpose is to generate meetings) and by the note that omitted inputs are reported back rather than invented. There is no explicit when-to-use versus when-not guidance and no routing to alternatives like thought_leadership_series or sales_enablement_content. The compliance instruction about written customer approval is a prerequisite, not usage guidance.

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