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

Annotations already declare readOnlyHint, idempotentHint and closed-world, and the description adds a layer beyond them: "recomputed live," hard refusal thresholds (10,000 source tickets, 500 emitted entries, 256 KiB result) and the guarantee that it "never returns partial totals." Those limits and the all-or-nothing contract are exactly the operational context an agent cannot get from the annotations.

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?

Well front-loaded: purpose first, then the payload detail, then read-only/liveness, then usage guidance, then limits. The dense parenthetical enumerating fields is information-bearing rather than filler, though the single very long opening sentence is harder to parse than it needs to be.

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?

There is no output schema and no parameters, so the description carries the full burden of explaining the return shape, and it does so in detail (entry granularity, per-epic progress fields, triage strip contents). It also discloses refusal conditions and the no-partial-totals guarantee, leaving nothing material for an agent to discover only at call time.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description correctly avoids inventing parameter detail and instead spends its space on output semantics.

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 ("Projects overview of the caller's board") and then enumerates exactly what each entry contains: recursive descendant progress, done %, counts by status, blockers, points, sub-epics, last activity, plus an unrouted-work triage strip. This is clearly distinguishable from siblings like ticket_list or ticket_burndown 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?

Explicitly names the moment to use it ("before planning a session to see initiative health at a glance") and routes the agent to the alternatives for follow-up ("use ticket_list/ticket_get to drill into any id it returns"). Both the when and the not-this-but-that alternative are stated outright.

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