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

Annotations cover the safety profile (readOnly/idempotent/non-destructive), and the description layers on substantial extra behavior: Mon/Thu 09:00 UTC refresh cadence, an auto-publish rule with corroboration thresholds, absence of human review before publication, staleness reporting via meta.data_freshness.stale, superseded-event markers, and anonymous-caller timeline truncation with the API-key remedy.

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 identity, then return shape, then cadence/provenance, then USE/DO NOT USE routing, then filters and citation — a logical order where nearly every sentence carries information. It is dense and slightly long, with the citation and API-key notes arguably better placed outside the selection path, but there is little true waste.

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 compensates by naming both return structures (matrix rows with date, source URL, confidence; timelines with status-change history back to 2022 and the sampling → qualified → volume_shipping progression) and provenance/freshness caveats. Combined with annotations and filter docs, an agent has everything needed to call and interpret it.

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 carry the load, and it lists every filter with added semantics ('customer' as a substring match, enum values for vendor/generation tied to the domain, include_timelines' link to history depth and anonymous truncation). Gap: no defaults are stated (e.g. whether include_timelines defaults on), so an agent cannot predict default output shape.

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 states a specific resource (Sourced HBM qualification tracker) and the exact relationship it covers — memory vendor × AI-accelerator customer × generation × stack height — with named concrete entities. It is immediately distinguishable from siblings like get_hbm_market_data and get_accelerator_costs.

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?

Explicit 'USE THIS for' block with sample queries (Vera Rubin HBM4 supply, Samsung/NVIDIA qualification, Micron HBM4 status) and an explicit 'DO NOT USE for' block routing pricing/market share to get_hbm_market_data and per-chip cost to get_accelerator_costs. 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.