gtm-alpha-consultant

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

Annotations already declare readOnly, non-destructive and closed-world, so the safety profile is covered. The description adds behavior beyond that: with no output schema, it is the sole source of return-value detail (score bands, lead motion, warnings, sector objections) and it discloses the conditional degradation to "preliminary" when optional inputs are missing.

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 purpose then inputs then outputs, with no filler. The parenthetical enumeration of all eight optional inputs is slightly redundant with the schema but serves as a quick completeness checklist.

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 12-parameter, read-only scoring tool with no output schema, the description does the heavy lifting: it explains the return shape and the preliminary-result condition. Remaining gaps are routing relative to siblings and any hint of latency or determinism, which are secondary for a pure computation call.

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, giving a baseline of 3. The description adds some meaning by separating required inputs (challenge, stage, industry) from optional ones and stating the consequence of omitting the optional set, but it restates the optional parameter names rather than adding format or decision guidance.

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 purpose (choosing a go-to-market motion) and enumerates exactly what the tool returns: EPIC scores 1-10 across five motions, the lead motion, warnings/notes, and sector buying-committee context. That output list distinguishes it from a generic consultation tool, though it never names or contrasts the siblings generate_roadmap and gtm_consultation.

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 when the tool applies ("helps you decide which go to market motion fits your company") and gives one real usage rule: supplying optional inputs yields a full score, omitting them yields a preliminary result. It does not state when to prefer this over gtm_consultation or generate_roadmap, nor any prerequisites or exclusions.

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, destructiveHint false and openWorldHint false, so safety needs little explanation. The description adds real behavioral context beyond that: the output shape, the conditional omission of self-serve steps for non-subscription business models, and the statement that it builds text from inputs only, which is consistent with the closed-world hint.

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 short sentences, front-loaded with the core purpose before the inputs and output. The self-serve omission rule is stated twice (once in the description body and once again effectively in the business_model schema text), which is minor redundancy but not harmful.

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 carries the burden of telling the agent what comes back, and it does: immediate, short-term and medium-term steps. All three parameters are enum-constrained and documented in the schema, leaving little an agent needs that 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 coverage is 100%, so the baseline is 3; the description earns above baseline because it decodes the EPIC letters (Ecosystem and ABM, Product-Led Growth, Inbound and Outbound, Community-Led), which the schema only lists as single letters. It also reinforces the conditional behavior of business_model, though that is largely duplicated from 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?

States a specific verb and resource: it produces a 30/60/90-day roadmap for one EPIC motion, and names what the output contains (immediate, short-term, medium-term steps). It does not explicitly distinguish itself from the siblings epic_audit and gtm_consultation, so an agent must infer that this one plans forward rather than audits or consults.

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 when to use it by describing the required inputs (an EPIC motion plus a time frame), which gives an agent enough to recognize a planning request. There is no explicit when-not guidance and no mention of when epic_audit or gtm_consultation would be the better choice.

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, openWorldHint=false, destructiveHint=false), so the description is free to spend its words on outcomes, which it does: per-motion 1-10 rubric scores, primary/secondary motion selection, 30-day steps, sector notes, and the preliminary flag. It doesn't state determinism or latency, but for a read-only scoring endpoint the disclosure is strong beyond the annotations.

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 lead sentence is well front-loaded and the closing sentence about the preliminary marker earns its place. The middle sentence, though, largely enumerates parameters the schema already documents, which is filler in a three-sentence description and makes the prose run-on.

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, no output schema, and only one required field, the description carries the burden of explaining what comes back and does so: four rubric scores, motion ranking, 30-day plan, sector notes, and the preliminary qualifier. What remains thin is the boundary with sibling tools, not the mechanics of the call itself.

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 would be 3, but the description adds real meaning on top: it separates the required GTM challenge/stage/industry from the optional ACV, deal cycle, NRR, TAM, self-serve, deal source and geography, and explains the consequence of omitting them. It also frames sector notes as conditional on inputs naming the sector, linking the industry parameter to an output effect.

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 verb+resource: it scores four EPIC GTM motions and produces the first 30 days of steps for the primary one. An agent can tell this is a diagnostic/planning tool rather than a roadmap generator. It never names the siblings (epic_audit, generate_roadmap), so the boundary with those tools has to be inferred from the output description.

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 'Helps you decide which go to market motion to lead with', and the description usefully explains that omitting optional inputs yields a result 'marked preliminary', which is real guidance about how much to invest in the call. However, there is no explicit when-to-use-vs-epic_audit or when-to-use-vs-generate_roadmap routing, which is a clear gap given three sibling tools.

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