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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is fully covered. The description adds only that it concerns authorship and contact, not the shape or content of what comes back, which is a modest addition over 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?

A single front-loaded sentence with no filler. The phrasing 'Who built this playbook' is slightly indirect for a tool whose scope is the vendor rather than the playbook, but nothing 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?

No output schema exists, so the description should signal what the caller gets back. It names two categories (authorship, contact) but not the fields, links, or company details returned, leaving a small but real gap for a simple informational tool.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 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 subject and outcome: identifying who built the playbook and how to contact them. It is clearly distinguishable from the sibling tools (list_stages, get_agent, build_prompt), which all operate on agents/workflows, so an agent can tell this is the vendor/contact-info tool 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 phrase 'for custom AI agents or MCP builds' implies the situation that selects this tool (a user wanting custom work or vendor contact), but there is no explicit when-to-use or when-not-to-use statement and no named alternative.

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 that this is a safe, read-only, idempotent, non-open-world operation. The description adds useful context: that it returns text only and that nothing is sent anywhere, which clarifies the output is a local artifact. It stops short of describing the prompt's structure, length, or what happens with an unrecognized agent name.

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 tight sentences with zero waste. The core action is front-loaded and the return-behavior caveat follows immediately.

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

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

For an eight-parameter tool with no output schema, the description is thin: it says the result is text but not what that text looks like or how the optional context fields shape it. The most important missing fact is whether the 'agent' value must match an existing agent (e.g., from list_agents/get_agent) or can be arbitrary.

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 all eight parameters are already documented in the schema. The description adds only the framing that the prompt is 'filled with your context' and targeted at 'one agent,' which does not expand on any individual parameter's meaning or format.

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 and resource: 'Create a complete, copy-ready prompt for one agent.' It is clearly distinct from siblings like list_agents or get_agent, but it differentiates itself only by implication, not by naming an alternative.

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 no explicit when-to-use guidance, no prerequisites, and no mention of alternatives or when not to use it. The only hint about intended usage is 'filled with your context,' which implies the optional parameters.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered elsewhere. The description contributes the identifier range (1-100) and accepted formats, but says nothing about failure behavior for an unknown agent or what 'full spec' comprises.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One front-loaded sentence with no filler; the key noun phrase and the identifier forms arrive immediately. It is efficient, though it spends words on the range where a clause on return shape might have been more valuable.

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

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

For a one-parameter read tool with full schema coverage and complete annotations, the definition covers what an agent needs to invoke it correctly. The only gap is the unspecified shape of the returned 'full spec', which is minor given there is no output schema to contradict.

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 example already shows '26' and 'cold-email-copywriter', so the description is largely restating the parameter. It does add the numeric bound 1-100, which the schema omits, but that is marginal added meaning.

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 ('Get') and resource ('full spec of one agent') and enumerates the accepted identifier forms (number, slug, name), which clearly separates it from list_agents and search_agents. It stops short of explicitly naming those siblings, so a 4 rather than 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?

The single-agent framing implies you use this when you already have a concrete identifier, but the description never says when to prefer this over search_agents or list_agents, nor what to do if the identifier is unknown. Usage is inferable, not stated.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and idempotency are covered. The description adds the dual fetch-vs-list behavior, but says nothing about failure modes (unknown workflow key) or what a returned workflow record contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with zero padding, front-loading what the tool returns before the call-mode instruction. Every clause carries information the agent needs.

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 single-optional-parameter read tool with full schema coverage and rich annotations, the definition covers purpose and both call modes. The remaining gap is the absence of an output schema combined with no description of the returned structure beyond "ordered chain of agents."

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 single parameter is documented with an example key, so the baseline is 3. The description goes beyond that by explaining the semantic consequence of omitting the optional parameter, which the schema alone does not convey.

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 pairs a specific verb with a well-defined resource and even defines the resource ("a ready-made, ordered chain of agents for a common job"), so an agent knows what a workflow is without opening the schema. It stops short of naming how it differs from siblings like get_agent or recommend_agents, which keeps it out of the top band.

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?

"Omit the name to list all workflows" gives a concrete mode-switch instruction that covers the two ways to call it. There is no guidance on when to reach for this tool rather than recommend_agents, build_prompt, or list_agents, and no mention of what happens with an unrecognized name.

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, idempotentHint and destructiveHint=false, so safety is fully covered by structured data. The description adds only that the filter is optional and where stage keys come from; it says nothing about ordering, result size, or what an agent record contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence, front-loaded with the core action and scoped with the optional filter. The parenthetical cross-reference is short and directly useful; no 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?

For a one-parameter read-only list tool with rich annotations, the essential call information is present. The remaining gap is that with no output schema, the description never indicates what a returned agent looks like, which matters for deciding follow-up actions like get_agent.

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 schema example ('copywriting') already anchors the stage parameter. The description goes beyond that by pointing to list_stages as the authoritative source of valid stage keys, which is genuine added meaning.

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 ('List') and resource ('lead-generation agents') with the optional filter named inline. It does not distinguish itself from the sibling search_agents, so an agent must still infer whether listing or searching is appropriate.

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 covers the filtered and unfiltered cases ('optionally filtered by stage key') and routes the agent to list_stages for valid keys. However, it gives no condition for choosing this over search_agents or get_agent, which is the main sibling ambiguity here.

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 readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds useful behavior beyond them by disclosing the fixed cardinality (12 stages) and that each item includes an agent count, implying a small deterministic payload. It does not say whether counts are live or whether stage ordering is stable, which is the remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that front-loads the cardinality and the resource, then the returned attribute. There is no filler and nothing an agent must read past to act.

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 zero-parameter read tool with annotations covering safety and no output schema, the description supplies enough: it states the fixed number of results and what each result contains. The only missing piece is a hint about how the returned counts relate to the sibling agent-listing tools.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The sentence correctly implies no filtering or paging inputs are needed.

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 ('List') and resource ('the 12 lead-generation funnel stages') plus what each entry carries ('how many agents each contains'), so the agent knows this is a fixed-size overview of stage buckets. It is clearly distinct from list_agents, get_agent, and search_agents by resource, 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?

Usage is implied rather than stated: this is the natural first call to orient in the funnel before drilling into agents. There is no explicit when-to-use guidance, no statement of when to prefer list_agents or search_agents instead, and no prerequisites mentioned.

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 establish read-only, non-destructive, idempotent, closed-world behavior. The description adds useful output context ('short, ordered list' with 'matching workflows'), but does not explain ranking criteria, result freshness, or other behavioral details 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 description is a single compact sentence with the core action and outcome front-loaded. Every phrase contributes to understanding, with no redundant wording.

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

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

For a simple two-parameter read-only recommendation tool, the description, annotations, and schema together cover the essentials. The main remaining gaps are explicit sibling routing and details about ranking or the limit parameter, but these are modest given the structured metadata.

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 both the goal and limit parameters are documented in the schema. The description reinforces the goal parameter's intent but adds no syntax, examples, or limit semantics beyond what the schema already provides.

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: give a goal and receive an ordered list of agents plus matching workflows. It clearly identifies the resource and goal-driven recommendation behavior, though it does not explicitly distinguish this from siblings like search_agents or list_agents.

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 implied usage guidance by telling the agent to describe what it wants to achieve. However, it does not say when to use this instead of search_agents, list_agents, or get_workflow, nor does it provide 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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds the useful detail that matching spans names, goals, inputs, and outputs, but says nothing about match semantics (substring vs token), ranking, or empty-result behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero filler; the covered fields are listed immediately after the core action. Nothing is wasted and nothing needs reordering.

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

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

For a simple two-parameter read-only search with full schema coverage and strong annotations, this is close to sufficient. What is missing is the routing information an agent needs to pick this over list_agents or recommend_agents, which matters given seven search-adjacent 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%, with 'query' documented as keywords and 'limit' capped at 25 with a default of 10. The description's only addition is clarifying which fields the query is matched against, which is mildly useful but does not explain syntax, multi-word handling, or limit behavior — baseline 3.

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 (keyword search) and resource (agents) and enumerates the searched fields: names, goals, inputs, and outputs. It is clearly distinguishable from get_agent or list_agents, 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?

It states what search does but gives no when-to-use guidance: nothing says when to use this versus list_agents, get_agent, or recommend_agents, nor whether it suits discovery versus exact lookup. The usage context is only implied by the words 'keyword search'.

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