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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial behavior: latest-state vs full-series modes, node conversions appearing as shifting node-class rows, joined metadata and availability_status, sourcing taxonomy + confidence, is_projection flag, and tiered access (free preview vs Pro/Enterprise full series, empty series for anonymous). Well beyond annotation coverage.

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-loads the resource definition, then routes with clear USE/DO NOT USE headers and a compact filters line. Information-dense, though the opening paragraph is a heavy parenthetical wall that could be trimmed; every sentence still carries useful content.

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?

For a 7-filter, no-required-param read tool with no output schema, the description covers data sources, units, return shape (per fab·class rows with metadata, availability_status, sourcing, projection flag), access gating, and citation format. Nothing an agent needs to call it correctly is missing.

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 0%, so the description must carry all parameter meaning, and it names every filter and explains the non-obvious ones: as_of as a latest-state cutoff, series as a mode switch, and limit as fab·class rows vs newest readings depending on mode. It provides semantics but not syntax detail (e.g. accepted foundry/country values) for the categorical filters.

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 resource (per-fab, per-tech-node-class capacity) and its data sources (fabs + fab_capacity_snapshots time-series), including units (kwspm frontend, k units/month backend). It names the covered vendors and explicitly distinguishes itself from siblings get_wafer_pricing and get_foundry_allocation. An agent can identify it without opening the schema.

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 explicit 'USE THIS for' examples ('what is TSMC's 3nm-class installed capacity?', 'which fabs are fully booked?') and a 'DO NOT USE for' clause naming the alternatives (get_wafer_pricing's foundry context, get_foundry_allocation) plus the reason (different granularity, deliberately separate). Routing is unambiguous.

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