Project brief (call first)

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

Annotations already establish readOnlyHint and idempotentHint, so safety is covered; the description adds that the output is token-budgeted and substitutes for exploratory reads, which is real behavioral context. It omits the 30s caching behavior and scan cost, though the schema's refresh param hints at it.

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?

Two sentences, imperative opener first, then a packed content list. Every clause earns its place and nothing is padded.

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?

With no output schema, the description carries the burden of describing return content, and the enumerated section list does that well. It could say more about output shape (structured vs prose) or how budget_tokens truncates sections, but an agent has enough to call it correctly.

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%, so both refresh (30s cache override) and budget_tokens (400–8000, default 1200) are already documented in the schema. The description adds no parameter meaning beyond noting the brief is "token-budgeted"; baseline 3 applies.

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?

"Start here" plus a concrete enumerated payload (detected stack, run/test commands, files to read first, git state, TODOs, decisions, gotchas, logs) states the verb and resource precisely. It distinguishes itself from siblings like recall/context_pack by framing the output as a synthesized session-start brief rather than a lookup.

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?

"Start here" and "at session start" give a clear triggering condition, and "replaces exploratory file reads" tells the agent what to skip. It does not name when NOT to use it or which sibling to prefer for follow-ups (recall, context_pack), so it stops short of full routing guidance.

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