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

Annotations already declare readOnlyHint, openWorldHint=false, and destructiveHint=false, but the description adds substantial behavioral context beyond them: it does not fetch URLs, does not establish authenticity/ownership/price, is free/read-only/no account, and declares data classification. This is rich, non-contradictory disclosure.

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 purpose and core input structure. Every sentence contributes useful information: input shape, return format, limitations, and cost/auth details. The long field-alias list is necessary but makes the paragraph dense; slightly better formatting would help.

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?

No output schema exists, but the description explains return values (per-field AGREES/CONFLICT/SINGLE_SOURCE, resolution guidance, verdict, receipt). It covers safety and data-classification constraints well. The main gap is that optional metadata parameters are not explained, though the core comparison workflow is complete.

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. It does so well for the core required parameters and evidence_items: it names many expected field aliases (creator/artist, title/name, date/mint_date/created, edition, contract/contract_address, token_id/identifier, chain, medium, claim+claim_key, source_url) and notes data_classification defaults to PUBLIC. However, four optional top-level parameters (synthetic, episode_id, continuity_handle, independent_operator_id) remain unexplained.

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 (Compare) and resource (public digital-art / NFT records) with field-by-field scope. An agent can tell exactly what the tool does without opening the schema. No siblings exist, so sibling differentiation is moot.

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?

Provides clear context for when to use it: comparing marketplace, block explorer, and artist catalogue records. Also gives when-not guidance ('URLs are not fetched; does not establish authenticity, ownership or price') and preconditions ('inputs must be public and non-personal'). No alternative tools are named, but none exist.

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