portfolio_digest

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

With no annotations provided, the description carries the full behavioral burden and delivers: 'Nothing is stored; every call recomputes from source', rendering is fixed server-side, and warnings must report stuck dispatches 'as unfinished, never as live'. It even warns against the likely agent mistake of re-summarizing the output. This is rich behavioral disclosure well beyond the bare schema.

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 well-structured and front-loaded: the critical paste-verbatim instruction leads, followed by usage context, section breakdown, parameter semantics, and behavioral notes. It is on the longer side and contains some explanatory flourish (the token_usage comparison clause), but for a tool with four parameters and four output sections, nearly every sentence earns its place.

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?

Given the tool's complexity — 4 params, structured multi-section output, cron integration, no annotations — the description is complete. It covers purpose, output handling, data source, section semantics, parameter meanings, and delegation boundaries, and even anticipates the likely misuse of re-summarizing. The presence of an output schema means it needn't enumerate return fields, and it still sketches the sections.

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 0%, so the description must compensate — and it does for all four parameters. `workspace` is given full semantics (None/name/"__all__" with a pointer to `list_projects`), `since_hours` maps to concrete values (24 daily, 168 weekly), `quiet_days` is defined as the idle threshold for the uncommitted-work warning, and `include_quota` is linked to the quota section. Every parameter gains meaning beyond its type/default.

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 first line states a specific verb+resource: 'Pre-rendered portfolio summary for push delivery' with the critical instruction to paste `digest_markdown` verbatim. It differentiates from siblings explicitly ('unlike `orchestration_history` — work that never went through central-mcp ... is counted') and names the analogous `token_usage.summary_markdown`. An agent can immediately tell what this is and how it differs from the dispatch/project-management siblings.

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?

The description gives explicit when-to-use context: the resident-agent digest loop (cron forwarding portfolio state each morning) or a terminal orchestrator handling daily/weekly recap requests. It also states what belongs elsewhere: 'Scheduling and alert watermarks belong to the caller (`list_dispatches` with `status="failed"` + `since` covers the alert half)'. This is clear routing with a named alternative and a condition.

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