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

Annotations only mark it non-readonly and destructive; the description goes far beyond, disclosing that it fires project rules with the 'versionReleased' trigger, notifies webhooks, does not block on unfinished issues, reports open counts and up to twenty issue names, defaults releaseDate to today overriding a planned date, and is a no-op on already-released versions. That is exactly the kind of side-effect and edge-case detail an agent needs before mutating.

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 primary behavior and the reversal are front-loaded, then side effects, then permission limits. It is dense and long, with the embedded JQL examples ('fixVersion in unreleasedVersions()') being the most expendable digression, but little else is redundant.

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?

With no output schema, the description still explains the meaningful return signals ('open' count, 'openIssues' sample, 'already': true). It covers permissions, defaults, side effects, and idempotency — nothing an agent needs to invoke it safely is missing.

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 baseline is 3, but the description adds meaning the schema does not: releaseDate omitted writes today and overwrites a planned date, and released=false is a reversal rather than a separate operation. Version lookup by name or id is already in the schema, so the lift is moderate rather than extensive.

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?

States a specific verb and resource — 'Mark a version released' — plus the inverse operation via released=false. It clearly separates this from create_version and update_version by describing the released mark specifically, and defines what a version is in the product's terms.

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?

Gives concrete conditions: check 'open' before releasing, project lead or admin only, and idempotent re-release returns 'already': true. It names adjacent tools (list_versions, list_project_rules) as prerequisites, but never explicitly says when to use update_version instead for other version field changes, which is the sibling most likely to be confused with it.

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