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

With no annotations, the description carries the safety burden alone. It discloses the composite read shape (handoff + snapshot + tasks + activity), which is real behavioral context, but never states read-only/no-side-effects, doesn't say what happens when no handoff exists, and gives no bounds on 'top open tasks' or activity window.

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-loads what is returned before the when-to-call triggers, and every clause carries information. The trigger list is somewhat long, but each phrasing maps to a distinct user intent rather than padding.

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, so the description must characterize the return payload — and it does, naming all four sections. No annotations means it could say more about read-only safety and empty-handoff behavior, but for a one-parameter aggregate read it is close to sufficient.

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 100% for the single board_id parameter, so the schema already documents it. The description's 'for a board' adds no syntax, format, or constraint information beyond what the schema provides — baseline 3.

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?

Specific verb+resource ('Get the full project context for a board') with an explicit enumeration of contents: session handoff, attention snapshot with its five buckets, top open tasks, recent activity. This distinguishes it from siblings like get_digest, my_work, list_tasks, and get_board_prompt without opening any 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?

Gives concrete invocation conditions ('Call this at the START of a session') plus literal user phrasings ('continue where we left off', 'what's the state of the project'), and names the specific scenario that selects it over alternatives — a new chat after a handoff was saved. No inference required.

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