reconcile_figures

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

With no annotations, the description carries the full burden and does substantial work: it enumerates the three deterministic resolution strategies, promises no Vision-model calls, states ambiguous cases are deferred, and guarantees Research Markdown is never modified. It does not describe how index rows are mutated or whether changes are reversible, so it falls short of a 5.

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?

Purpose is front-loaded, followed by scope rules and then a clean Args block. Every section earns its place, though the evidence list and the args list could be marginally tightened.

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 explained, and the description covers scope, deterministic behavior, and all params. For a moderate-complexity tool with no annotations, it is largely complete, missing only detail on how index rows are written.

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 0%, so the description must compensate, and it documents all three params: note_paths (vault-relative Markdown paths, max 20), dry_run (report without downloading/updating), limit (1-20). The behavioral meaning of dry_run and the path semantics are genuinely additive, though it adds little beyond the schema's constraints.

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 (reconcile) and resource (figure files and index rows), then narrows it with 'without Vision-model calls,' which distinguishes it from vision-based siblings like extract_figures_for and read_figure. An agent can tell what this does and roughly where it sits relative to figure-handling tools.

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?

The phrase 'without Vision-model calls' and 'Ambiguous cases remain in the manual queue' imply a deterministic-only lane, but no sibling is named and there is no explicit 'use this instead of X when Y'. Usage is inferable rather than stated.

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