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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses quota consumption, a daily check schedule, 30-day slot lifetime with no auto-renewal, the already_watched no-op on repeat calls, and that skills never enter the Claude Code allowlist. The repeat-call statement is scoped to an active watch, and slot expiry plus per-slot quota consumption still make repeated calls non-idempotent, so it is consistent with idempotentHint=false rather than contradicting it; failure modes (invalid ID, quota exhausted) are not covered.

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 text is dense and front-loaded: purpose first, then constraints, repeat behavior, and lifetime, with no filler sentences. The telegraphic style ('Daily schedule, subject to source quota') is slightly clipped but each clause carries information an agent needs.

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 one-parameter tool with no output schema, the description supplies the lifecycle (30-day slots, no renewal), quota caveat, prerequisite (skill collection enabled), repeat-call outcome, and a cross-system consequence (allowlist exclusion) — enough to call it correctly. It omits what a successful watch returns and how quota exhaustion surfaces, which keeps it from a 5.

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?

There is a single required parameter with 100% schema description coverage, and the schema already explains the `mcp_…`/`skl_…` listing_id format. The description only implies the target via 'remote MCP or supported SKILL.md' and adds no format or sourcing detail beyond the schema, so the 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?

The description opens with a concrete verb+resource: 'Watch a remote MCP or supported SKILL.md', which is unmistakably a subscription-creation action and clearly distinct from siblings like unwatch_tool and list_watched_tools. It also sharpens scope with 'Skills cover text and review signals, not execution', so an agent knows exactly what is being watched.

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?

It gives real eligibility conditions — the target must be a live remote MCP or a skill whose public raw.githubusercontent.com SKILL.md is supported, and skill collection must be enabled first. It does not explicitly contrast this tool with alternatives (e.g., get_listing, list_watched_tools) or state when watching is the wrong move, so it stops short of full when/when-not guidance.

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