annotate_figure

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

With no annotations, the description carries the full burden and delivers: it discloses that insights for the same figure are appended (not overwritten), that the note backlinks the paper, and that the note is sized to stay within the search index window. The recommended structured-fact format ('panel C: IC50 = 2.3 µM') is a concrete behavioral convention the agent could not infer from the schema.

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 purpose, then workflow guidance, then an Args block — a clean hierarchy where each sentence carries information. It is somewhat verbose with the caching rationale repeated, but nothing is filler. Slightly trimmer would reach a 5.

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 three-required-parameter mutation tool with no annotations, the description covers purpose, prerequisites, storage semantics, and every parameter, and an output schema already exists so return values need no explanation. Nothing an agent needs to invoke this correctly 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 description coverage is 0%, so the description must compensate, and it does via an explicit Args section for all three parameters: note_path (vault-relative path of the source paper note), fig_index (0-based, cross-referenced to search_figures/read_figure), and insight (the fact/observation). Every parameter gains meaning beyond its bare name and type.

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: 'Save a read-time insight about a figure as an atomic vault note.' It distinguishes itself from general note tools like append_to_note by scoping the artifact to figure-derived insights that backlink the source paper. An agent can tell what this produces without opening 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 states when to use it — 'AFTER you have loaded a figure (read_figure) and reasoned out something worth keeping' — naming the prerequisite sibling tool and the trigger condition. It also gives the payoff rationale (future questions answered from text without re-loading the image). It does not explicitly contrast against the closest alternative (append_to_note), which keeps it from a 5.

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