Hub Watch

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

With no annotations, the description carries the full behavioral burden and does most of it: blocking semantics, that press/form lines reach only the agent that sent the message unless every=True, that quiet=True surfaces policy-set-aside lines, that phone/VR input is read-only, and the trust/use/kind taxonomy. Gaps: it never says what happens on timeout or what wait_min's unit and default (100) mean, which matters for a blocking call.

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 purpose is front-loaded and the operational instruction follows immediately, which is good. But the middle is a dense semicolon-chained wall that enumerates the return JSON field by field — much of which the output schema already states — making the passage harder to parse than its content requires.

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?

For a blocking, nine-parameter watcher with no annotations, the definition covers the important ground: re-arm discipline, filtering flags, provenance fields, and claim etiquette. The remaining holes are the timeout/wait_min behavior and any error or empty-wake case; the return-shape explanation is partly redundant given an output schema exists.

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 supply all nine parameters' meaning, and it supplies most: mine, every, quiet, kinds, people, places, since (via 'remembers its place' and {lines, since}), and who (via the example). wait_min is never explained, and 'since' semantics as a resume cursor are only implied.

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 opening sentence gives a specific verb and resource: it 'blocks until someone sends something, returns it, and remembers its place' — a long-poll watcher, distinct from one-shot reads. It also names hub_claim as the sibling used to claim a line before acting. It does not distinguish itself from hub_read, chat_watch, or phone_watch, which read as adjacent 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?

Usage is unusually concrete: run it in the background via `python -m ismail hub_watch "who=Maintainer"`, act on the result, and re-arm it FIRST after every wake. It also states the condition for using hub_claim instead ('when others watch too'). What is missing is when to prefer this over hub_read or the phone/chat watchers, so the alternative selection is only partially covered.

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