watchRepo

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions publishing a NIP-51 kind 10018 list, but does not disclose that this is a replaceable event that may overwrite the user's existing followed-repos list, nor does it clarify whether it is additive or destructive. The 'full `a` tag set' phrase is ambiguous and could mislead an agent about side effects. More transparency is needed for a write operation.

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 a single, tightly worded sentence that front-loads the action ('Watch a repo') and packs essential context into a parenthetical. Every phrase contributes meaning, with no filler or repetition. It is an appropriate length for the tool's complexity.

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?

The tool writes a replaceable NIP-51 event, yet the description omits critical context such as overwriting behavior, required authentication (though privkey is auto-loaded), return value (no output schema), and how it interacts with unwatchRepo or listWatchedRepos. With no annotations and no output schema, the description is too thin to fully inform an agent about side effects or expected results.

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 covers 75% of parameters with basic descriptions (ownerPubkey, repoId, privkey), leaving relays undefined. The description's mention of 'full `a` tag set' hints that ownerPubkey and repoId form an address tag, adding some meaning beyond the schema, but it does not explain how each parameter is used or clarify the optional relays parameter. The description contributes moderate value but does not fully compensate for the gap.

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 clearly states the tool's function with a specific verb and resource: 'Watch a repo'. It further specifies the protocol (NIP-51 kind 10018) and the action (publishes full `a` tag set), and draws a comparison to the 'gittr Watch button' for clarity. This distinctly separates it from siblings like starRepo, unwatchRepo, and listWatchedRepos.

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 implies when to use the tool (to watch/follow a repo) and provides operational context (publishes NIP-51 list). However, it does not explicitly state when not to use it or name alternatives such as unwatchRepo or starRepo, so it falls short of the highest bar but still conveys clear intended usage.

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