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

Annotations include readOnlyHint=true, and the description confirms 'Read-only; no side effects,' which is redundant but consistent. It adds a small behavioral note that the slug must come from next_steps or get_plan, which is an input provenance constraint. No additional behaviors like auth, rate limits, or error cases are disclosed, so with annotations present the bar is lower but the description offers modest extra context.

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 dense paragraph that front-loads the purpose ('One plan step in full') and enumerates the returned fields. Every sentence contributes: the field enumeration, the usage instruction, and the read-only note. It could be slightly more concise, but it's appropriate for a complex return value.

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 must explain what is returned – and it does, listing all major components (title, detail, URL, play, prerequisites, verification, minutes/cost, founder_steps). It also provides usage context. It doesn't mention error handling or return format, but for a read-only retrieval tool with high schema coverage, it's sufficiently complete.

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 has 100% coverage describing all parameters, so baseline is 3. The description adds value by telling the agent the slug should come from next_steps or get_plan, which is beyond the schema's general description. It doesn't mention the free-tier behavior of done/traits/not_applicable, but the schema covers that.

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 ('step'), and explains it returns the full step details. It distinguishes from siblings by referencing next_steps and get_plan as the source of the slug, making it clear this tool is for retrieving a single step's details, not for listing steps or plans.

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 tells the agent to read this before working a step returned by next_steps or get_plan, and that the slug comes from those. This gives a clear when-to-use trigger. It does not explicitly state when not to use it or name alternatives, but the behavior is well implied.

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