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

Annotations only carry readOnlyHint=false and openWorldHint=false, so the description carries the full burden of behavioral disclosure. It delivers rich context: owner-only access, entry into the normal review gate, the listing-owned version rule ('never to a version declared in a repo'), and per-kind handling (re-pull, re-scan, re-version). This goes well beyond the sparse annotations.

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 long but well-structured, front-loading purpose and usage before detailed per-kind behavior and parameter notes. Most sentences earn their place, though the extraneous mention of non-schema fields adds noise and the length could be tightened without losing meaning.

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 multi-kind, owner-only mutation tool, the description covers routing, ownership, review gate, version ownership, and sibling preference; output schema and full parameter descriptions fill the rest. The only substantial gap is the discrepancy between mentioned fields and the actual schema, which leaves a minor hole in the invocation contract.

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 100%, so the schema already documents each parameter. The description adds useful conditionality (ref only for code-bundle/skills-bundle, changelog 'where the kind takes one', bump default patch) but also references fields (system_prompt, tools, guardrails, etc.) that are not present in the input schema. This mismatch can mislead an agent into attempting unsupported parameters, offsetting the added value.

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 clear verb-resource statement ('Publish a NEW VERSION of YOUR OWN agent') and immediately establishes scope by covering all agent kinds. It explicitly names and contrasts with sibling tools (findagent_bump_version, findagent_repull, findagent_reintrospect_mcp), so an agent can disambiguate this tool without inspecting schemas.

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 explicit when-to-call guidance ('Call this when a creator asks to update, re-publish, re-pull, re-scan or bump their agent') and explains the key simplification ('you do NOT need to know which mechanism its kind uses'). It also explicitly states preference over three alternatives and the reason they are inferior, making the routing decision unambiguous.

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