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

Beyond the readOnly/idempotent annotations, the description discloses important behaviors: large results may be saved to a file, results should be retained in execution storage before bounded display, next[] must be followed in order, and the complete profile should be reused before searching notes. It also explains special metadata flags such as meta.onboarding, meta.saveDrought, and meta.truncated.*, along with workspace-only invocation limits. These are substantial behavioral details that annotations alone do not provide.

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 most important instruction, calling once at the start before replying, is front-loaded. However, the description is a dense single paragraph with many compact clauses and cryptic field references, making it harder to scan than necessary. It is information-rich but would benefit from clearer separation of invocation rules, output handling, and metadata semantics.

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 no output schema and two optional parameters, the description covers the important context: what the session payload contains, how to handle large results, how next[] should be followed, how truncated inventories should be drilled into, and how special metadata flags should alter behavior. It also documents workspace restrictions and the distinction between projectKey and Penny Projects. That is complete enough for an agent to use the tool 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?

Schema coverage is 100%, so the schema already documents both optional parameters. The description still adds useful meaning: tz controls local Today/Overdue and dueNow boundaries, and projectKey includes only the matching repository subconscious block while explicitly not representing a Penny Project. It also clarifies the workspace-only limitation around project-scoped access, which is more than the schema alone conveys.

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 makes clear that this is a session-start bootstrap that returns a reusable profile, inventories, next steps, and metadata, rather than a general read tool. It distinguishes itself from siblings by directing drill-downs to penny_read and onboarding to penny_start_setup. A direct one-line statement of the returned payload would make the purpose unmistakable, but the overall intent is easily inferable.

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 call this ONCE at the start of every conversation before the first substantive reply. It also names alternatives and exclusions: use penny_read for truncated inventories or skills, offer penny_start_setup when meta.onboarding is present, and use penny_read target:projects view:scopes for workspace-only connections. This leaves little ambiguity about when and when not to invoke it.

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