Reconcile the brain — contradictions between cards + unrecorded migrations

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

No annotations are provided, so the description carries the full burden. It clearly states safety: 'Reads ONLY the filesystem — never the database, never the network — and changes nothing.' It discloses persistence semantics for false-positive dismissals, marks candidates as 'candidates only, YOU confirm each', and notes that claims/plans are 'never auto-archived'. This is unusually transparent.

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 the tool is genuinely complex and the text is scannable with bolded section labels. It front-loads the core purpose and each sentence carries behavior or usage content. A little trimming would be possible, but the density and structure earn a high score.

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 tool with no output schema, no annotations, and three optional parameters, the description covers the modes, expected findings, interpretation cues, safety profile, and follow-up workflows. It tells the agent what the tool will surface, what requires user confirmation, and how to persist dismissals. Combined with the detailed schema enum descriptions, nothing essential is missing for correct invocation.

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 100%, so the baseline is 3. The main description reinforces what mode means but adds no parameter-level detail beyond the input schema's own descriptions of mode, root, and canvas. It does not introduce new syntax, defaults, or relationships between parameters, so it neither compensates nor falls short.

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 'Truth maintenance' and then names precise actions: 'finds same-subject live card pairs', 'lists committed migration files', and 'pre-v1.15 raw-bash ship cards to tidy'. It clearly identifies the resources being reconciled and separates this from siblings like read_canvas or brain_challenge. The title's 'reconcile' jargon is fully resolved by the body.

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 explicitly says when to run it: 'Run it periodically, or when recall surfaces something you believe is stale.' It also routes follow-up actions to siblings, telling the agent to retire stale cards via brain_note and dismiss false positives via brain_connect with relationship 'not_contradiction'. It does not list explicit when-not-to-use alternatives, so it stops short of 5.

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