mnemosyne_agent_collisions

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

The readOnlyHint is consistent and the description adds substantial non-obvious behavior: it reads transcript files from disk, needs neither Mnemosyne OS nor a token, resolves each directory to a working tree, and explicitly discloses that unreadable sessions are omitted and unplaceable sessions are listed separately. This gives an agent a clear model of what the tool can and cannot detect.

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 dense but every sentence earns its place: purpose, triggering scenarios, mechanism, and limitations. The critical before-commit guidance is front-loaded, and the later caveats about transcript readability and unplaceable sessions are important enough to justify the length.

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 description covers when to use it, how it works, its data source, and its limitations, and the schema documents the only parameter. The one gap is the absence of output/response shape details, especially since there is no output schema; an agent cannot confidently predict the exact format of a collision report. This is minor but prevents a 5.

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?

The single optional `project` parameter is already fully described in the schema, including exact matching, path normalisation, passing `git rev-parse --show-toplevel`, and omission meaning 'check every project'. The description adds context about working-tree resolution but does not need to repeat the parameter details. Baseline 3 is appropriate given the 100% schema coverage.

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?

Opens with a specific verb and scope: 'Check whether two agent sessions are live in the same git working tree and branch right now, across every installed harness.' This is a distinct operation and clearly not the same as the sibling memory, todo, or agent tools. The title 'Check agent collisions' reinforces the same purpose without needing the schema.

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?

Explicitly instructs when to call it: 'Call it before `git add -A`, before a commit, and before a rebase'. It also explains why via the shared git index, which helps an agent decide to insert this check into Git workflows. No near-sibling alternative is needed because the use case is unique.

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