resolve_act_scan

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

Adds real behavioral context beyond the annotations: no OCR or image downloads by default, optional local readers producing 'bounded evidence and candidates', and the rule that AMBIGUOUS/PROBABLE results are not confirmed acts. This tells the agent what the tool will and won't do operationally. The readOnlyHint=false annotation is not explained by the description, though it is not directly contradicted either (local index/cache writes are plausible).

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?

Four short sentences, front-loaded with the selector constraint and default mode; little waste. The telegraphic phrasing ('bounded evidence and candidates') is compact but slightly cryptic.

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 selector rule, default mode, and ambiguity caveat are covered, and an output schema exists so return shape need not be described. However, for a 7-parameter tool with zero schema documentation, the semantics of name, act_number, and max_scans are absent, leaving the agent guessing on non-trivial inputs.

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?

With 0% schema description coverage across 7 parameters, the description must carry the load; it usefully disambiguates 'date means act date' and states the mutual exclusivity of record_id/source_url, and loosely characterizes reader as an 'installed local reader'. It says nothing about name, act_number, or max_scans, so several parameters remain undocumented anywhere.

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 clear verb+resource ('Resolve an act') and immediately scopes it with the input selector rule ('exactly one of record_id/source_url'). It implicitly separates the tool from download_act/download_scan by declaring metadata-only default, but it never names or contrasts a sibling explicitly.

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?

Gives a hard usage constraint (exactly one of record_id/source_url) and states the default operating mode, which implies when to leave readers off. It never says when to prefer resolve_act_scan over search_acts, get_record, or download_act, so routing is left to inference.

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