project_bind

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

Annotations declare readOnly=false and destructive=false; the description reinforces this with 'Never creates or deletes' and adds genuine context beyond annotations — the shared-vs-dedicated lifecycle and the stop_after_export grace/export window that lets the local controller stop the resource. This is rich behavioral disclosure not derivable from the hints alone.

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?

Front-loaded with the core action, then the ownership branches, the non-mutation guarantee, and the versioning requirement — each sentence carries information. The middle ownership sentence is dense and jargon-heavy, but nothing is wasted.

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?

An output schema exists so return values need not be described, and annotations cover the safety profile. However, for an 11-parameter binding tool with 0% schema coverage and a nested resourcePolicy object, several parameters and their valid values remain unexplained, leaving gaps an agent would hit when constructing the call.

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 description coverage is 0%, so the description must carry the burden. It explains the semantics of ownership, preparePolicy, resourcePolicy (with stop_after_export behavior) and expectedVersion, but leaves projectId, expectedAccount, repository, codespaceName, remoteProjectRoot, githubHost and locale entirely undocumented — partial compensation for an 11-param tool.

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: 'Persist ... binding locally', with the bound entities (account/repository/Codespace) named. An agent can tell this is a local persistence step distinct from prepare/release, though it never explicitly names the sibling it is not.

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?

Provides conditional guidance on ownership modes (shared -> reuse_only; dedicated -> start_existing/stop_after_export) which implies when each configuration applies, but never states when to choose project_bind over codespace_prepare or codespace_release, nor any prerequisites.

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