list_milestones

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the positive safety profile is covered. The description adds meaningful behavioral context beyond the annotations: the pipeline-scoping constraint, the exact fields returned, and the fact that milestones are tied to opportunity lifecycle actions. It accurately matches the read-only annotation and discloses that this is a lookup helper.

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 four sentences with no filler. It front-loads the primary purpose, then gives return fields, consumer tools, prerequisite, and a critical scoping warning. Every sentence earns its place and supports correct tool selection and invocation.

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 properly lists the returned fields (id, name, probability, position). It also covers usage context, prerequisites, and cross-pipeline constraints. The only minor gap is that pagination behavior is not mentioned, though the optional page/perPage parameters are evident from the schema and are secondary to the core milestone lookup.

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 0%, so the description must compensate. It clearly explains the key required parameter pipelineId by referencing 'a specific opportunity pipeline' and telling the agent to discover pipelineId via list_pipelines. However, the optional page and perPage parameters are not described at all, leaving their semantics to inference from their names. This is partial compensation, not complete.

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 and resource: 'List milestones (deal stages) within a specific opportunity pipeline.' It also enumerates the returned fields (id, name, probability, position), clearly distinguishing this from generic list operations. The tie-in to create_opportunity and update_opportunity removes any ambiguity about the tool's 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?

The description explicitly explains when to use this tool: when creating opportunities (pass milestoneId to create_opportunity) or moving them across stages (set milestoneId in update_opportunity). It also gives a prerequisite ('Discover the pipelineId first via list_pipelines') and a hard constraint ('Milestones are pipeline-scoped — not interchangeable across pipelines'), which functions as a when-not guidance.

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