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

Annotations already declare readOnly, idempotent, non-destructive, openWorld. The description adds real behavior beyond that: results are sorted newest-first and the response carries count/truncated so a large match set is never silently cut. That truncation and ordering contract is the useful part an annotation cannot express.

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?

Two dense sentences: the filter dimensions first, then the return-shape contract. No filler, no restatement of the title, and the pagination behavior is front-loaded where the agent needs it.

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?

With no output schema, the description usefully covers sort order, default cap, and truncation signals, and annotations carry the safety profile. Minor gaps remain — whether multiple filters combine as AND, and the offset paging default — leaving it just short of fully self-contained.

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 100%, so the schema already documents all seven parameters, making 3 the baseline. The description reinforces domain examples and the FLOP threshold, but adds no syntax or format detail beyond the schema (its domain examples even diverge slightly from the schema's "Speech").

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 (search/filter) and resource (Epoch AI's models database) and enumerates the filterable dimensions (organization, domain, year, min compute). It does not reference the sibling ai_model (likely the single-record fetch) or ai_compute_trend, so an agent gets no explicit routing signal, but the core purpose is unambiguous.

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?

Usage is only implied by the filter list — the description never says when to pick this over ai_model or ai_compute_trend, nor any exclusion. It reads as adequate context for a filtered-list tool but the agent must infer routing itself.

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