GetSales: Outreach MCP Server

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

Annotations only declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false; the description adds real context beyond that: it proxies to a domain mount, dangerous targets gate on a preview/confirm handshake, and cross-team calls require an OAuth grant covering the target team plus live membership. It also discloses that responses echo the effective team as meta.team_sid. It does not describe how upstream tool errors or denials surface back to the caller.

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 action, then the safety handshake, then the cross-team mechanism. Dense but every clause carries operational information; no filler or restatement of the title.

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 proxy tool with a nested free-form arguments object, the description covers the routing prerequisite, the mutation-safety flow, auth requirements for cross-team execution, and the team echo in responses. That is sufficient to call it correctly, though error/timeout behavior of the delegated call remains unaddressed and there is no output schema to fall back on.

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 earns extra credit by clarifying that commit_token must be nested inside the arguments object rather than passed top-level, and by explaining that team_sid is top-level and triggers a token swap. That is meaning not derivable from the generic 'The tool's arguments object' schema description.

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: invoke a named tool with its arguments object, and explicitly ties the name to search_tools. It distinguishes itself from the sibling discovery tools (search_tools, describe_tool, list_toolsets) as the execution endpoint.

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 clear routing (find the name with search_tools first) and the two-step preview-then-confirm workflow for dangerous tools, including where commit_token goes. It also states when to use team_sid. It stops short of explicit when-not-to-use guidance or naming alternatives for execution paths.

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, closed-world and non-destructive, so the safety profile is fully covered without the description. The description adds only the shape of the return (description, input schema, safety flags) and the pre-first-call timing, and says nothing about behavior on unknown tool names or the opt-in _meta forwarding that the schema mentions. Adequate but thin given how much the annotations already carry.

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, zero waste. The returned content is stated first and the usage rule second, so the reader gets both the what and the when at a glance.

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 lookup with no output schema, describing the payload (description, input schema, safety flags) effectively covers the return value, and the usage rule is supplied. Minor gaps: behavior for a nonexistent tool name and the analytics caveat in _meta are left entirely 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 description coverage is 100%, including the note that the name must be exact and comes from search_tools or list_toolsets. With the schema doing the heavy lifting, the baseline of 3 applies; the description adds no meaning about the name argument or the _meta analytics object.

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 and resource — it returns the full definition of one tool (description, input schema, safety flags). That's clearly distinct from passing arguments to a tool, but the siblings (search_tools, list_toolsets, call_tool) are never named, so the differentiation is left implicit.

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 concrete trigger: read it before the first call of a tool whose definition you don't yet have, so arguments are correct. That's a clear when-to-use rule. It stops short of saying when to skip it (e.g., when you already have the definition) or naming search_tools as the recommended preceding step, though the parameter schema does supply that routing.

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 genuinely new operational context: the OAuth Bearer token requirement, which the annotations do not convey, plus a concrete inventory of what the payload contains. It stops short of noting response size or rate limits when include_tools is true.

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?

Highly dense and front-loaded: the resource description comes first, the sibling routing second, the auth prerequisite last, with no filler. It is written as one long compound sentence, which makes it slightly harder to scan than it could be, but nothing is redundant or padded.

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 describing the return shape at both levels (toolset and optional per-tool entries with safety flags). Combined with the named prerequisite (OAuth Bearer token) and the zero-required-parameter signature, an agent has everything needed to call it correctly on the first attempt.

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 still earns a point by explaining the tradeoff behind include_tools — that tool entries omit descriptions and parameters because search_tools and describe_tool carry those — which frames why an agent would or wouldn't set it. The _meta analytics block is left 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?

Opens with a concrete metaphor-plus-verb framing ('The map of this server') and then enumerates exactly what is returned: every toolset with id, title, one line, and tool count, optionally each tool's name, title, and safety flags. It explicitly differentiates itself from all three siblings by assigning each a distinct role.

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?

Explicitly routes the agent: use search_tools to find a tool by capability, describe_tool to read one definition, call_tool to execute, leaving list_toolsets as the orientation step. The condition for the include_tools variant is also spelled out, so selection between tools and between parameter modes is unambiguous.

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 (read-only, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real context: what a lite result contains (name, toolset, title, one line, parameter names), what full adds (complete definition with input schema), and the default row counts. It says nothing about the opt-in analytics forwarded via _meta, which is only disclosed 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?

Front-loaded with purpose, then query phrasing, then the detail switch, then a closing precondition — a logical order with no filler. The result-fields sentence is a slightly dense list but every clause carries information an 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?

With no output schema, the description carries the return-value burden and does so adequately by enumerating lite fields and describing the full variant. Combined with the parameter defaults and the pre-call rule, an agent has enough to select and invoke it correctly; only the _meta analytics side effect is left undocumented.

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 baseline is 3, but the description goes beyond it by tying detail="full" to a behavioral consequence (safe to call at once) and by giving query phrasing examples. The default counts for limit are stated, though the _meta analytics parameter is not discussed at all.

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?

"Find tools by what they do" gives a specific verb (find) and resource (tools), and the description makes clear this is discovery rather than execution. It does not name its siblings call_tool/describe_tool outright, but the closing rule "Have a tool's full definition before its first call" implicitly separates it from call_tool.

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 concrete invocation guidance — phrase the query as object + action, use toolset to narrow, use detail "full" when you expect to call the result immediately. The one gap is that it never explicitly says when to prefer the sibling describe_tool instead of detail="full".

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