start_here

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

Annotations already declare readOnly/idempotent/closed-world, but the description adds real behavioral context: the exact contents of the brief, the character budget, and the non-obvious side effect that it 'opens a FlowState session automatically'. The automatic session creation is a disclosed state change that sits in mild tension with readOnlyHint=true, though it is a bookkeeping effect rather than a data mutation.

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 the imperative 'CALL THIS FIRST' and then the payload description. It loses a point for repeating the size values that the schema already documents (quick/standard/deep and the 4,000/12,000 limits appear in both places).

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?

No output schema exists, yet the description enumerates what the brief contains, its size cap, and the fallback behavior, which is everything an agent needs to call it correctly. Nothing material is left unspecified.

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 adds meaning beyond the schema: project accepts a name or id, folder is matched to a project when project is omitted, and omitting all arguments returns the project list. These usage semantics are not derivable from the field descriptions alone.

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 and resource ('Returns a brief' with the project's hard rules, todos, problems, changes, decisions) and distinguishes itself from siblings like get_context and list_projects by declaring it is the entry point ('CALL THIS FIRST'). An agent can identify the tool's role without opening the schema.

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?

Explicit when-to-use ('in every conversation about a project') plus an explicit fallback path for the edge case: call with no arguments, or with folder, when the project is unknown. This is the rare definition that routes the agent through both the happy path and the failure path.

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