Image Report

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

No annotations are provided, so the description carries the full behavioral burden, and it discloses almost nothing: it does not say whether the tool is read-only or writes artifacts to disk, whether it requires a loaded catalog, or whether it is expensive on large corpora. With an output schema present the return shape need not be restated, but the absence of any side-effect or cost disclosure is a real gap for a report-generation tool.

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?

A single front-loaded sentence with a colon-delimited list and no filler, so it is efficient and scannable. It loses a point because the compressed noun list leans on undefined jargon rather than stating the operation in a verb-first form.

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 output schema covers return values, which lowers the bar, but for a two-parameter tool with zero schema description coverage and no annotations the description leaves both the path format and the optional media directory unexplained, plus the read-only versus file-writing behavior is unstated. An agent could pick the right tool but would still be guessing at invocation details.

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% for both parameters, so the description must compensate and does not. 'Across one or more catalogs' hints that catalog_paths is plural but the schema types it as a single string, leaving the agent to guess whether it is comma-separated, a glob, or repeated; collection_media_dir is never mentioned at all and its purpose (media root override?) is entirely undocumented.

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 names the resource ('one or more catalogs') and enumerates the concrete contents of the report (totals, figures, tables, noise, sync ratios), so an agent can tell this is an aggregating summary tool rather than a mutation tool like card_patch_apply or batch_auto_fix. It stops short of a 5 because the action is expressed as a noun phrase ('Summary report') with no sibling named, and terms like 'noise' and 'sync ratios' are undefined domain jargon.

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?

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites (e.g., whether catalogs must be loaded first via catalog_load), and no alternative tool is named. The agent must infer from the sibling list alone whether image_report or corpus_digest/deck_audit is the right summary surface.

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