publishNostrPages

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

With zero annotations, the description carries the full burden. It discloses significant behavioral details: requires index.html, defaults to blossom.gittr.space, supports fromBridge mode to read git tree, and excludes app installers from the default Blossom. It doesn't disclose whether the operation is destructive/reversible or what auth/privkey permissions are needed, but the two-step process and file requirements are genuinely informative beyond the schema.

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?

Three sentences with high information density: protocol, workflow, requirements, default server, and exclusion. The critical constraints are front-loaded (NIP-5A, requires index.html, fromBridge option) before the default. Minor inefficiency: the parenthetical 'NIP-5A kind 35128' and 'kind 24242' are redundant for precision but not wasteful.

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 13-parameter publish/mutation tool with no output schema, the description explains the main flow well: what uploads happen, what manifest signing means, what prerequisite exists (index.html), and the alternative input mode (fromBridge). It lacks edge info like whether overwrites happen, paywall implications (sibling getPushPaywallStatus exists), or validation of the returned manifest, but the essential invocation logic is covered.

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 coverage is 54%, so the description partially compensates by explaining the file upload flow and the fromBridge alternative. It explains the semantic relationship between files/fromBridge/branch/prefix and the Blossom proxy workflow. However, it doesn't add meaning for un-described params like dTag, repoId, privkey, ownerPubkey, relays, title, description, server—the agent will rely on names/schema for those. Baseline 3 is appropriate because the description adds some meaning but doesn't fully cover the remaining 46%.

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 verb (Publish), resource (Nostr Pages NIP-5A kind 35128), and the two-step process (upload static files via Blossom proxy, then sign manifest). It distinguishes itself from siblings by naming the Blossom proxy specifically for Pages and explicitly says never for app installers. The technical anchors (NIP-5A, kind 35128, kind 24242) give an agent precise matching capabilities.

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 gives explicit when-to-use context: upload static files through Blossom proxy for NIP-5A named sites, requires index.html, can pass files or fromBridge:true to read git tree. It also includes one exclusion (not for app installers). It doesn't explicitly name alternative sibling tools, but the NIP-specific and workflow-specific context implies usage; a clear when-not-to-use statement exists for the default Blossom.

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