get_facts

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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description's contribution is the extra semantics: 'This read never projects cached cards or starts model work' discloses side-effect scope, and 'source_supported means an exact source quote, not established truth' warns that returned facts are not verified truth. It adds a citation discipline ('Cite evidence citation_id') that the annotations cannot express. It does not disclose result shape or pagination behavior.

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?

The lead sentence is front-loaded and does the routing work immediately, and later sentences are short and purposeful. The second and third sentences are fragmentary ('candidate and possible_conflict remain uncertain') and lean on undefined vocabulary, costing some readability.

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 defines three result-state labels (source_supported, candidate, possible_conflict) and the citation_id convention, which is real value. But a four-parameter filtered-list tool with zero schema coverage leaves the agent guessing about filtering, paging, and the include_history parameter, so it is only minimally complete.

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% across four parameters (limit, query, source_id, include_history), so the description must carry the burden and largely does not — it never explains filtering, what source_id scopes to, or what limit applies to. Worse, the description directs agents to get_fact_history for past observations while the schema itself exposes an include_history flag, leaving that tension unresolved.

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 names a specific verb and resource: 'Read grouped exact card facts/decisions with permitted evidence', and explicitly excludes generation ('no generation'), which separates it from model-inference siblings. It also names get_fact_history as the alternative for past observations. It falls short of 5 only because terms like 'grouped' and 'card' are undefined jargon an agent may not resolve without prior schema knowledge.

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?

It gives one explicit routing rule: 'use get_fact_history for past observations', plus the negative condition 'no generation'. However it gives no guidance on when to prefer this over search_memory or get_record, both of which likely return overlapping memory content.

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