compare_filings

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

Annotations already establish the read-only, idempotent, closed-world, non-destructive profile, so the description's added value is the semantic flag vocabulary it returns (`is_new_in_b`, `is_removed_in_b`, `is_sign_flip`, `has_restatement_warning`) and the restatement semantics itself, which is non-obvious behavior. It does not cover failure modes (mismatched fiscal year ends, missing prior filing), keeping it 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?

Front-loaded with the one-line purpose, then trigger examples, then return semantics, then parameter overrides, then sibling disambiguation — a sensible order. Slightly long, and the inline backtick code spans make it dense, but every block earns its place.

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 shape needn't be explained, and annotations carry the safety profile. What remains uncovered is the directionality convention of year A vs year B and the `fiscal_period_type` parameter, both of which an agent could get wrong on a 6-parameter tool.

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 carries the param burden. It handles `hub_concept_codes` well (optional, None = default hub set, explicit override up to 50) and `form_type` well (enumeration of accepted forms and the omit-for-most-recent-original default), but `entity_id`, `fiscal_year_a`/`fiscal_year_b` ordering convention, and the `fiscal_period_type` default of 'FY' are undocumented in both schema and description.

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 ('Compare two annual filings') and narrows scope explicitly with 'of the SAME entity side-by-side,' which immediately separates it from the cross-entity sibling. The capitalized SAME is a deliberate disambiguator.

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?

Gives literal trigger phrasings ('what changed at X between FY{n-1} and FY{n}', 'year-over-year breakdown') plus an explicit exclusion block naming three siblings (compare_entities, get_amendment_diff, get_metric_history) with the condition that selects each. Nothing is left to inference.

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