prepare

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

With no annotations, the description carries the transparency burden. It discloses that it returns multiple data components, that lessons have surface_id and should be followed and marked with mark_lesson_followed, and that it is fast (~10ms). However, it doesn't mention whether the call is read-only or has side effects, nor error handling for unknown projects.

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 compact, front-loaded with the READ-FIRST key phrase, and packs multiple pieces of information (returned items, lesson follow-up, performance) into two sentences without fluff.

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 tool with one parameter and an output schema, the description gives a good overview of the returned components and the lesson-follow-up workflow. It could add a note about behavior for unknown projects, but overall it's sufficiently complete for an agent to invoke correctly.

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 schema has a single 'message' parameter with no description (0% coverage). The description compensates by showing prepare(message=<the user's message>) and explaining that message is the user's message, which adds semantic meaning beyond the bare 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?

The description clearly states this is a READ-FIRST bundle for the start of work on a known project, returning project_context, surfaced lessons, recent_activity, and open_goals. It also says it replaces several recall() calls, which distinguishes it from the recall sibling.

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 explicitly says to use it at the start of work on a known project, and notes it replaces several recall() calls. This provides clear when-to-use context and directly names an alternative (recall).

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