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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds substantially more: the exact fields returned, the source-quality signal (as_of and source_url only for employer-confirmed entries), the no-match fallback behavior, and specific negative cases (Amazon, ExxonMobil colleges-only). That is real behavioral context beyond the structured fields.

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 purpose and mostly efficient, but the opening sentence is a long run-on carrying two parenthetical example lists that could be trimmed. The remaining clauses (negative examples, disclaimer, no-match fallback) each earn their 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?

With no output schema, the description carries the return-shape burden and does so: it lists the fields, source provenance, fallback path, and caveats for non-standard programs. An agent has everything needed to call it and interpret the result.

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% for the single parameter, so the baseline is 3; the description earns an extra point by disclosing exact-match semantics ('Without an exact match, returns self-serve discovery instructions') and sample employer values, which shapes how the agent should phrase the argument.

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 (lookup) and resource (employer matching-gift program) and enumerates the exact payload returned: match status, match rate, annual cap, platform, source note, as_of/source_url. An agent can distinguish this from siblings like get_donate_options or find_foundation_prospects without opening any 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?

Usage context is clear (supply an employer name to learn whether a matching-gift program exists), and it even mandates post-call behavior: 'Always tell the donor to confirm current terms.' It does not, however, name a sibling alternative for other giving questions, so it falls short of explicit when-not/alternatives guidance.

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