craft-gtm-mcp

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds useful output behavior: one battle card per competitor, competitor details mapped to the named competitor, each objection answered, and strengths/gaps kept in the user's own words; it lacks failure or limitation details, so not 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 description is a single dense paragraph with the purpose front-loaded and no obvious filler. It could be more readable if split into purpose vs output-mapping sentences, but it is appropriately sized for an 11-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?

For a complex 11-parameter tool with no output schema, the description explains the input-to-output mapping and what each battle card contains, which is enough to invoke it correctly. It does not fully specify the internal structure of the battle card, so a 5 would be too generous.

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 11 parameters in detail. The description restates several fallback behaviors and the competitor-detail mapping, adding only 'each objection gets its own answer' as a small semantic addition beyond the 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?

State specific evidence: it says it returns one battle card per named competitor built from strengths, weaknesses, competitor details, objections, wins and losses. That is a clear verb and resource, but it does not explicitly distinguish itself from the sibling GTM tools.

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 usage for competitive battle-card preparation, but it gives no explicit when-not guidance and does not name alternatives among siblings such as craft_gtm_analyzer or pmf_scorecard.

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 this is a read-only, non-destructive, closed-world operation, so the safety profile is covered. Beyond that, the description adds genuinely useful behavior: grading is grounded only in the document's content, timeline scoring counts real dates/durations/quarters, and the answer shows the plan's own line per dimension plus missing elements and suggested sections. What it omits is the scoring scale or criteria behind each CRAFT dimension, which is the main thing an agent would want to interpret 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?

Two sentences, front-loaded with the decision the tool supports and followed by concrete output behavior. It is dense but almost every clause carries information; the 'Timeline counts real dates...' clause is the only one that reads as a detail hung off the main thread.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description must explain the return value, and it does: a score per CRAFT dimension, the plan's own line per dimension, named missing elements, and suggested sections. What remains unexplained is the score range and what distinguishes a passing plan from a failing one, which an agent would need to report results meaningfully.

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 six parameters and the enums, making the baseline a 3. The description adds no parameter-specific meaning and, importantly, does not resolve the overlap between 'industry' and 'your_sector', which both carry near-identical enums and subtly different explanations.

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 and resource: it takes 'the text of a GTM document or plan' and 'returns a score for each CRAFT dimension'. An agent can tell this is a document-scoring/readability tool rather than an analysis generator like competitive_intel or crisis_planner, but it never explicitly distinguishes itself from the closest sibling, pmf_scorecard.

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 implies usage ('decide whether a GTM plan is clear enough to run', 'paste the full text') and scopes the analysis to 'based only on what the plan contains'. However, there is no explicit when-to-use vs when-not guidance and no named alternative for adjacent needs such as scoring product-market fit.

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?

The annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds genuinely new behavior: the default crisis set is not ranked by likelihood, sector notes come from `your_sector` or are inferred from the caller's wording and stay neutral when unclear, and inferred business model is reported back. It still says little about how long the playbooks are or what structure they take, which matters given 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?

Three sentences, front-loaded with what it does before moving to the optional-input consequences. Every sentence carries information, though the crisis-default and compliance-item points duplicate the schema text almost verbatim, which is the only 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 nine-parameter tool with four required fields, six enums and no output schema, the description covers purpose, the optional-input behavior, and the shape of the return at a level sufficient to invoke it correctly. A short note on the volume or structure of the returned playbooks would close the remaining gap left by the missing output 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 description coverage is 100%, so every one of the nine parameters is already documented in the schema, including the fallback behavior for `potential_crises` and the use of `compliance_requirements`. The description restates those same points rather than adding syntax, formatting, or interaction detail, 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 names a concrete verb and resource ('decide who does what when a crisis hits') and states the output ('returns crisis playbooks with a response team and notification steps for each crisis'). Together with the named inputs (company, industry, customer base, data sensitivity) an agent can tell instantly this is a crisis-response planning tool, and no sibling in the list overlaps with that scope.

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 gives clear operating context ('when a crisis hits') and explains the two conditional paths: supply `potential_crises` to get exactly those playbooks, or omit it to fall back to a sector default set. It also tells the caller the effect of supplying compliance items. What it lacks is any explicit when-not or alternative-tool routing, though none of the siblings are real substitutes.

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, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds real behavioral detail beyond that: sector language is used in the questions, the sector can be auto-derived from inputs, hypotheses are 'kept whole' (not paraphrased away), and synthesis templates are bundled into the output. It does not state length or format of the guide, 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 is front-loaded in the opening clause and the remaining clauses add substantive facts (sector language, hypothesis preservation, synthesis templates). It is a single dense run-on sentence, however, and the mid-sentence restatement of how sector is resolved is slightly redundant.

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 an 8-parameter, enum-heavy generator with no output schema, the description does what matters: it explains what comes back (an interview guide plus synthesis templates) and how optional inputs are inferred when omitted. Minor gaps remain around guide length and how product_complexity and business_model alter the output.

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 enum parameters already carry their own explanations, so the schema does most of the work. The description only echoes that the sector may be supplied or inferred and that hypotheses are preserved; it adds no format or precedence guidance beyond what the schema says.

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 artifact: it takes interview type, product context and persona and 'returns an interview guide'. The phrase 'decide what to ask customers to test your hunch' pins the resource (customer interview questions) clearly enough that an agent can distinguish it from siblings like pmf_scorecard or competitive_intel, though it never names those siblings 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?

Implicit usage context is present ('test your hunch'), which signals a pre-research/discovery moment, but there is no explicit when-to-use versus when-not, and no alternative tool is named. An agent must infer that this is for planning interviews rather than analyzing 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?

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the lower bar applies. The description adds genuine behavioral context: tasks and messaging are derived from the sector and business model read from the inputs, each goal is filed under its own metric, and when no sector is supplied the tool infers it and names what it read (or stays neutral if unclear) – useful disclosure of inference behavior for an agent.

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 what and the return shape before the input-format detail; there is little waste. Some content repeats the schema (date formats, sector fallback), which would be the first thing to cut.

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 an 11-parameter planning tool with no output schema, the description usefully characterizes the return value (phased plan, task list, messaging table, per-goal metrics) and explains how optional inputs influence the output. The remaining gap is the duplicate industry/your_sector parameters, which an agent must resolve without help from the description.

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 six parameters carry enums, so the schema already documents formats like 'TBD'/'Q2 2027' and the enum values. The description restates the date-format rule and the sector-inference behavior but adds no meaning beyond the schema, and it does not clarify the apparent overlap between the 'industry' and 'your_sector' parameters, which both enumerate the same values.

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 the verb and resource plainly (decide a launch plan from product/feature, launch type, segments and goals) and enumerates the outputs: a phased plan with tasks, a messaging table and success metrics. That output signature is distinctive among siblings such as craft_gtm_analyzer or competitive_intel, but no sibling is named explicitly, 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?

Usage guidance is confined to one input mode: supply a date for a dated timeline, or 'TBD'/'Q2 2027' for a flexible plan. There is no when-to-use versus when-not-to-use guidance relative to the other GTM planning tools, and no prerequisite or scope statement telling an agent when this is the wrong pick.

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 (readOnly, non-destructive, closed-world), so the bar is lower. The description adds genuine behavior: the output shape (tiers, commission rows, KPIs), that deal size scales example amounts while rates stay fixed, that a range is refused, and that omitted optional fields are inferred and the inference is reported back – a useful transparency trait. It does not describe output size, format or failure modes beyond the range refusal.

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 dense sentences, front-loaded with purpose then output shape, with no filler. It is information-rich rather than padded, though the second sentence packs several conditional facts together and would read better as short clauses.

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, 5-required analytical tool with no output schema, the description covers purpose, required inputs, return contents and optional-field fallback behavior. The remaining gap is the `industry`/`your_sector` overlap and what happens with partial or contradictory inputs.

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% with per-field descriptions and enums, so the baseline is 3. The description adds marginal meaning by saying program structure varies by partner model and that sector drives the named partner types, but it does not clarify the near-duplicate `industry` vs `your_sector` parameters, which is the one ambiguity an agent would actually need resolved.

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 ('decide what partner program to run and how to start it') and then enumerates the concrete deliverables: tiers, example commission amounts and KPIs. It is also clearly distinct from every sibling tool (pmf_scorecard, launch_commander, retention_playbook), so an agent can route 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?

The use case is explicit ('decide what partner program to run and how to start it') and it notes that existing partners are used 'when given', which tells the agent when to populate an optional field. It stops short of stating when NOT to use it or naming an alternative sibling for adjacent partner questions.

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/non-destructive/closed-world annotations, it discloses meaningful behavior: the business model is inferred from inputs when not supplied, the activation score is deliberately omitted for services, connectivity and investment businesses, benchmarks are 'example' ranges rather than authoritative, and unscored figures are surfaced as gaps. It does not describe the response format or how conflicts between a supplied segment and the inferred one are resolved in the output, but the annotations already lower the disclosure burden.

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 purpose is front-loaded in the opening clause, which is good, but the whole definition is one long comma-spliced sentence that piles secondary features (inferred business model, activation omission, feedback quotes) into the same breath. It is dense rather than wasteful, yet a short second sentence or bulleted clause would make the conditional logic far easier to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and seven parameters, the description does the necessary work of telling the agent what comes back: per-dimension scores, benchmark ranges, priority actions, data gaps and answered feedback. What is missing is any indication of the return format or structure, which an agent would otherwise get from an output 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 description coverage is 100%, so the schema already explains every parameter, including the enums and the sector-versus-target-market distinction. The description only restates the metric list and the business-model inference, adding little syntax or semantics beyond what the schema fields already contain.

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 resource: it takes product, target market and metrics and returns a scorecard that scores each PMF dimension against example benchmark ranges. It also defines scope precisely enough to separate this tool from siblings like retention_playbook or competitive_intel, and it spells out secondary outputs (priority actions, data gaps, feedback quotes).

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 gives a clear usage context – deciding whether you have product market fit and whether to scale – which is enough for an agent to know when to reach for it. It never states when NOT to use it or names an alternative sibling, so there is no explicit routing 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 establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds behavior beyond that: the shape of the output artifacts, the mode switch on churn_reasons, and the fact that optional interventions and data signals are consumed when supplied. It does not mention response length, latency, or how the sector inference fallback is signaled beyond 'names what it read' in the 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?

Three sentences, front-loaded with the purpose, then the fallback mode, then optional-input behavior. Every sentence carries new information and none restates the title. The sentences are long and clause-heavy, which slightly hurts scannability but not substance.

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 10 parameters and no output schema, the description must explain what comes back — and it does, listing health signals, interventions and an email draft per reason, plus the discovery-kit variant. Required vs optional inputs are handled by the schema. Minor gaps: nothing about output volume or how the two modes differ in size, but nothing an agent needs in order to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and four parameters carry enums, so the schema does most of the work and the baseline of 3 applies. The description does add genuine semantics for churn_reasons (blank triggers the discovery-kit branch) and for current_interventions (compared against the playbook). It says nothing about the near-duplicate industry vs your_sector distinction, leaving that entirely to the 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?

The description names a concrete deliverable — a retention playbook containing health signals, interventions and an email draft per churn reason — plus a second output mode (churn discovery kit). That is far more specific than the title 'Retention Playbook'. It never contrasts itself with any sibling tool, though the sibling set (pmf_scorecard, competitive_intel, crisis_planner) is topically distinct enough that confusion is unlikely.

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?

Explicit conditional routing is given: 'If you do not know why customers leave, leave the churn reasons out and you get a churn discovery kit instead.' That tells the agent when to omit an input and what changes as a result. It stops short of naming an alternative tool for adjacent jobs (e.g. PMF scoring or customer interviews), so no true alternatives guidance.

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