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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the bar is lower. The description adds genuine behavioral context beyond that: an open-case precondition and a party authorization rule. It still omits whether resubmission duplicates evidence (relevant given idempotentHint=false) and what happens to evidence after the case closes.

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 short sentences, front-loaded with the precondition and the highest-value parameter detail. The telegraphic "kind: delivery_proof (weight 3), log (2), or statement (1)" is dense but readable; no filler sentences.

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?

An output schema exists, so return values need no explanation. However, for a 4-parameter mutation tool with 0% schema coverage, the description leaves content unexplained and does not say what the weights mean for downstream evaluation — gaps an agent would have to guess at.

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 weight. It does a good job on kind, enumerating the three allowed values with their relative weights, but case_id, party (only hinted at via "named parties"), and especially content are left entirely undefined.

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 ("Submit evidence") and adds a real precondition ("while the case is open"), so an agent can distinguish it from read-side siblings like get_case and list_cases. It never explicitly contrasts with file_case or rule, so differentiation is inferred rather than stated.

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 two concrete selection constraints: the case must be open, and only named parties may submit. That is stronger than typical implied usage, but it offers no guidance on when a case should be filed versus when evidence should be submitted, and no alternative named.

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