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

Rich beyond the annotations: it discloses that the tool is served locally by board-mcp (no board-core route, direct call 404s), that data comes over `/ws` with the user's own token, 30-day retention, agent-token reads owner's inbox, and 503-implies-retry. It stays at 4 rather than 5 only because much of this is restated redundantly across paragraphs instead of stated once cleanly.

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?

Badly bloated: the title text is repeated verbatim at the start, the 'call this when a session starts...' sentence appears twice, the prompt-injection warning about `text` appears twice, and the agent-token ownership note appears twice. The genuinely useful facts (404 behavior, 30-day retention, 503 retry) are buried in the duplication.

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?

Despite no output schema, the description enumerates every returned field (`id`, `at`, `kind`, `project_key`/`issue_key`, `who`, `via_agent`, `text`, `read`), explains paging, retention, and the error path. Nothing an agent needs to call and interpret the result is missing.

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 67% and covers `before` and `unread_only`, but the description adds the crucial paging recipe ('page with `before` = `next_before`') and clarifies `unread_only: true` for new entries. `limit` (default 20, max 30) is left undocumented in both places, so it misses the top mark.

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+resource ('your notifications ... as an agent reads them') and enumerates exactly what kinds of events appear (assignments, @mentions, replies, status changes, handoffs, project access). It also implicitly separates itself from read_inbox, which it names as the marking counterpart.

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?

'Call this when a session starts and whenever you finish a card' gives explicit trigger conditions, and the routing to read_inbox for marking entries read distinguishes the sibling pair clearly. It also disambiguates overlap with get_project `docs.open_handoffs_for_me` / list_docs `for_me`.

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