evaluate_context

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

Annotations already declare readOnlyHint=true, and the description adds meaningful operational context: this tool does not fetch or retrieve anything, only evaluates provided signals. This goes beyond the annotation's safety implication and clarifies the tool's pure judgment 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?

Two sentences with no wasted words. The core action and result are front-loaded, followed by precise exclusions that help differentiate from siblings.

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?

The description covers purpose and non-behavior, and the schema fully documents parameters. However, there is no output schema, and 'decision-ready output' is vague about what the agent should expect in the return value, which is a meaningful gap for a judgment tool.

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 100%, so the schema already documents each parameter. The description only adds a general phrase about 'caller-provided candidate context,' which maps to the signals parameter but does not enrich the semantics of profile, intent, or now beyond what the schema provides.

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 uses a specific verb ('Evaluate') and a specific resource ('caller-provided candidate context') and states the outcome ('decision-ready output'). It also distinguishes itself from siblings by explicitly listing operations it does not perform ('does not fetch, crawl, scrape, browse, read folders, or call adapters'), making its role clear.

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?

The description positions this as 'the primary FreshContext judgment path' and gives clear exclusions for when not to use it, implying fetch/crawl/scrape tools are for retrieval. It does not name specific alternative tools, but the sibling list makes the intended separation clear.

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