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 safety is covered. The description adds real behavioral context beyond that: derivation rules (strengths/gaps fall back to wins/losses 'in your own words'), routing of competitor details and objections, and inference behavior for omitted optional fields. It does not disclose limits such as a maximum competitor count or latency.

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 output ('one battle card per competitor') before the routing details. The second sentence is dense and slightly run-on, but every clause carries information rather than 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 11 parameters but full schema coverage and annotations covering the safety profile, the description's remaining job is to convey the return shape, which it does explicitly (one battle card per competitor containing strengths, weaknesses, competitor details, objection answers, wins/losses). Nothing an agent needs to invoke 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%, so the baseline is 3. The description goes further by explaining cross-parameter behavior the schema does not: each competitor detail is routed to the competitor it names, each objection gets its own answer, and strengths/weaknesses default from wins/losses in the user's own words.

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 uses a specific verb ('returns') and a concrete resource ('one battle card per competitor'), and enumerates the inputs that feed it (strengths, weaknesses, competitor details, objections, wins, losses). It is clear what the tool produces, though it never contrasts itself with sibling GTM tools like craft_gtm_analyzer or 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?

Usage is only implied: the agent can infer you call this when you need competitive battle cards, and the schema's required/optional split signals which inputs matter. There is no explicit when-to-use, when-not-to-use, or named alternative among 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 openWorldHint=false, so safety is covered. The description adds genuine behavioral context: scoring is grounded only in what the plan contains (Timeline counts real dates, durations and quarters), it quotes the plan's own line, names only missing elements, and suggests sections to add — a useful anti-hallucination guarantee.

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?

Purpose is front-loaded in the first clause and the two sentences carry no filler. The second sentence is a long run-on stacking four separate behaviors, which slightly hurts scannability but does not waste words.

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 must convey the return shape, and it does: an analysis with a score per CRAFT dimension plus missing-element callouts and section suggestions. For a read-only analyzer whose safety profile is already in annotations, this is nearly complete, though a hint about score scale or granularity would close the last 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 description coverage is 100%, including rich notes on industry/your_sector fallback behavior, so the baseline is 3. The description adds framework-level detail (how Timeline is scored) but no parameter-level meaning beyond what the schema already documents, and it does not explain how document_type or desired_outcome affect the analysis.

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 takes GTM document text and returns an analysis scored against the CRAFT framework, dimension by dimension. That is far more precise than a tautology, but it never names or distinguishes itself from siblings like pmf_scorecard or launch_commander, which also evaluate GTM-adjacent artifacts.

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 it should be called when a GTM document or plan needs scoring, but there is no explicit when-to-use, when-not-to-use, or alternative routing against the seven siblings. No prerequisites or input-format guidance beyond the schema is offered.

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 a safe read (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond them: the default crisis set is not ranked by likelihood, optional fields are inferred and reported back, and compliance entries are surfaced in the notification steps.

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 return value, then the optional-input behavior. The 'Name the crises you know of to get those playbooks' phrasing is slightly conversational but earns its place by conveying the optional-input contract.

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 output schema exists, and the description covers what comes back (playbooks with team and notification steps) plus defaults for the two most behaviorally significant optional params. That is enough for a read-only 9-param tool, with only minor gaps around how unlisted crises/inputs are validated.

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 the baseline is 3, but the description adds meaning the schema doesn't: it explains the fallback for potential_crises and that compliance_requirements are consumed by the notification steps. It also frames the four required inputs as the core driver of the playbook, though the industry vs your_sector distinction is left 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?

States a specific verb and resource ('returns crisis playbooks with a response team and notification steps for each crisis') and names the inputs that drive it. The output is concrete enough that an agent can distinguish it from the unrelated siblings (competitive_intel, retention_playbook, etc.) without opening any 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?

Gives conditional guidance for the optional fields: name crises to get those playbooks, or omit them and the tool falls back to a sector default set; compliance items feed the notification steps. It doesn't state when to prefer another tool, but the sibling set is a different domain, so no exclusion is genuinely needed.

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 confirm read-only, non-destructive, closed-world behavior, so safety needs no restatement. The description adds genuine behavioral value on top: sector is either chosen or inferred from inputs, questions adopt the sector's terminology, supplied hypotheses are preserved intact, and synthesis templates are bundled – all relevant for a tool with 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?

Two sentences, front-loaded with the input→output contract before the qualitative guarantees. Dense but every clause carries information; only mild redundancy in re-listing schema params.

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 tool with 5 enums and no output schema, the description covers input roles, inference fallbacks and the rough contents of the returned guide (questions, preserved hypotheses, synthesis templates). It does not describe guide structure or length, but nothing essential to invoking 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%, so the enum semantics for industry, your_sector, business_model, product_complexity and interview_type are already documented in the schema, including the fallback inference behavior. The description restates rather than extends that, 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?

States a concrete verb and resource: it takes interview_type/product_context/target_persona and returns an interview guide, and it names three shaping factors (interview type, sector, product complexity). An agent immediately knows this generates a research artifact rather than analyzing data. It does not contrast itself with siblings, though none of the listed siblings (competitive_intel, pmf_scorecard, etc.) overlap with interview-guide generation.

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 through the input names – the presence of interview_type with values like discovery/validation/churn signals this is for planning a customer interview. There is no explicit 'use this when' statement, no prerequisites, and no guidance on choosing between interview types or on when a different sibling tool would be better.

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 cover the safety profile (readOnly, non-destructive, closed world), so the bar is lower, and the description adds real context beyond them: it discloses the returned artifacts, how sector and business model are inferred from other inputs, and how goals map to metrics. It does not mention any rate limits or failure modes, but for a read-only generator this is solid disclosure.

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 outcome, then input-format guidance, then the sector/business-model nuance. Every sentence carries information, though the middle sentence is slightly circuitous and the goal-filing clause is a little dense.

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 11 parameters, no output schema, and six enums, the description compensates by naming the returned artifacts and explaining the inference fallbacks for optional inputs. An agent has enough to call it correctly, though the relationship between goals and the metrics table could be spelled out a bit more.

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 the baseline is 3, but the description goes further by explaining inference behavior for optional fields (sector and business model are read from other inputs and reported back) and the accepted launch_date formats with their planning implications. That meaning is not fully captured by 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?

States a specific action (takes launch inputs) and a concrete deliverable set: a phased launch plan with tasks, a messaging table and success metrics. That output signature clearly separates it from siblings like pmf_scorecard or craft_gtm_analyzer, so an agent can route without reading 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 description gives useful input-handling guidance (give a date for a dated timeline, use 'TBD' or 'Q2 2027' for a flexible plan) and explains that optional fields are auto-inferred. However, it never says when to choose this tool over the sibling planning tools, nor any prerequisites or exclusions, so usage 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?

Annotations already establish readOnly/non-destructive/local behavior, and the description adds real behavioral context: a deal-size range is refused, omitted industry/sector/business model are inferred from other inputs and explicitly named back, and the tool stays neutral when inputs are unclear. It stops short of describing output volume or limits, but goes well beyond the annotation baseline.

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 that lead with inputs and the returned artifact, then the conditional variations. Efficient and front-loaded, though the second sentence is long and packs several distinct behaviors together.

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 output schema exists, so the description carries the return-value burden and does so by naming tiers, commissions and KPIs. With 10 fully-described parameters and safe annotations, the only missing pieces are optional-input fallback details, which are partly covered.

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 the schema baseline is 3. The description adds meaning beyond it by explaining downstream effects: partner_goals becomes the target of the first KPI row, your_deal_size scales example commission amounts while rates stay fixed, and industry/your_sector drive sector-specific buyers and objections.

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 transformation: takes company, product, partner model, goals and deal size, and returns a partner program with tiers, example commissions and KPIs. It also names the six partner-model variants it structures differently, so an agent can distinguish it from generic GTM siblings like launch_commander or craft_gtm_analyzer.

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 required input set (you need a partner model and deal size, so this is a partner-program design task), and it explains that structure varies by partner_model. However it never states when to pick this over sibling GTM tools or any exclusions, leaving routing to inference.

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 openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it infers the business model from inputs when not supplied, conditionally omits the activation dimension, and quotes and answers customer feedback. It does not state limits on metric parsing beyond the schema's note that unscored figures are listed as such.

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 tight sentences, front-loaded with the core action and followed by the inference and dimension-exclusion rules; little waste. Slightly dense with metric enumeration that largely duplicates the schema, keeping it short of a 5.

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 reasonably: a scorecard scoring each dimension against benchmark ranges plus quoted-and-answered feedback. With read-only annotations covering safety, the remaining gap is depth of the output shape, which is described only at a high level.

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 seven parameters including enum meanings and optionality. The description restates the metrics input and business-model inference but adds no syntax or format detail beyond the schema, 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 specific verb+resource: it returns a product-market fit scorecard that scores each metric dimension against example benchmark ranges, with model-aware behavior (activation omitted for services/connectivity/investment). This is clearly distinguishable from the surrounding sibling playbooks, though it never names an alternative tool to route against, which is what a 5 would require.

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 rather than stated: an agent can infer it should call this when a PMF assessment is wanted, since the description explains the inputs it consumes. There are no explicit when-to-use/when-not-to-use conditions and no mention of when to prefer a sibling such as retention_playbook or craft_gtm_analyzer.

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), and the description goes further by disclosing what is produced (health signals, per-reason interventions and email drafts) and how behavior branches when churn_reasons is omitted. It does not mention length, cost, or rate limits, so not a full 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?

Three sentences, front-loaded with the core deliverable, and no wasted preamble. The churn-reasons fallback is stated twice (once in the opening, once in the final sentence), which is mild redundancy.

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 sufficiently sketches the return shape (health signals, interventions, per-reason email drafts, discovery-kit fallback). Combined with the 100%-covered schema, an agent has enough to call it correctly; only the volume/format of the output remains unspecified.

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 every parameter and the baseline is 3. The description adds cross-parameter behavior (business model drives health-signal weighting, sector notes come from your_sector/industry, current_interventions are compared against the playbook), which is useful but mostly echoes the schema text.

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 action (takes segment, business model, churn rate) and a concrete deliverable (retention playbook with health signals, interventions and email drafts per churn reason). It is unmistakably distinct from the sibling set (competitive_intel, crisis_planner, pmf_scorecard, etc.), none of which are retention-playbook 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?

It gives explicit conditional guidance: 'If you do not know why customers leave, leave the churn reasons out and you get a churn discovery kit.' That is a clear when-to-use-which-mode rule. It does not name any alternative tool or state exclusions relative to siblings, which keeps it 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.