get_timing_paths

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral detail by explaining what the tool returns ('worst critical paths... sorted by slack') and how parameters modify behavior (clock_filter filters by clock pair text, include_detail adds full cell/net breakdown). This goes beyond annotations to describe the output characteristics, though it stops short of specifying return format or pagination—acceptable given no output schema.

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 description is two sentences: the first front-loads the core purpose and sorting behavior, the second explains the two filter/detail parameters and points to the alternative tool. Every sentence earns its place—no redundancy, no fluff. The structure is ideal for quick agent parsing.

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?

For a read-only reporting tool with annotations covering safety, the description provides sufficient information to call it correctly: what it does, how parameters affect results, and when to use the sibling tool. It doesn't describe the return format, but that's not critical since no output schema exists and the tool's purpose is clear. The only minor gap is that it doesn't explicitly state that project is required (though schema marks it required), and it doesn't mention the default for max_paths—both are minor.

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 schema description coverage at 0%, the description must carry the meaning of parameters. It explicitly explains the two non-obvious parameters: clock_filter ('keeps paths whose launch vs capture clock pair contains the text') and include_detail ('adds the full cell/net breakdown'). It also implies that analysis is setup/hold via the enum and that max_paths controls count (inferred from name). While max_paths and project are not detailed, their meaning is self-evident. The description compensates well for the schema gap.

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 states a specific verb ('get') and resource ('worst critical paths') with a clear sorting criterion ('sorted by slack'). It explicitly distinguishes itself from the sibling tool run_sta_tcl by noting that custom queries should use that tool, preventing ambiguity. The purpose is unambiguous and immediately actionable.

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 explicitly tells the agent when NOT to use this tool: 'For custom queries (-from/-to/-through), use run_sta_tcl.' This is a clear exclusion and directs to the appropriate alternative. It also implies the typical use case: fetching worst paths with optional clock filtering and detail expansion. This level of guidance is rare and highly effective.

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