get_ui_state

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

No annotations are provided, so the description carries the full disclosure burden. It does substantive work: describes the returned payload contents, reveals the compact phrase-grouped markdown view is ~10x smaller than raw segments, and discloses speaker attribution, silence gaps, and optional energy peaks. This gives the agent an accurate model of what the response contains without needing to inspect the data.

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?

Purpose is front-loaded in the first sentence, followed by a high-value IMPORTANT call-order note, then parameter-specific detail. It runs a few lines longer than strictly needed ('the primary surface for reasoning about clip boundaries' is slightly ornamental), but every sentence adds real content and nothing is redundant.

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 simple read-state tool with one optional parameter and no output schema, the description is well-rounded: it covers the return contents, the transcript mode's behavior, call timing, and how results connect to sibling tools. The only minor gap is that it doesn't disclose error conditions or when the state might be uninitialized, which is low-risk for a read operation.

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 coverage is 100% and the schema already describes include_transcript ('Include full transcript segments... Set true when analyzing content for clip suggestions'). The description layers genuine extra meaning on top: setting it true 'analyzes transcript content' and returns a compact phrase-grouped markdown view with speaker attribution and silence gaps — explaining why the flag matters for clip-boundary reasoning beyond the schema's one-liner.

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 specific action ('Read the current podcli session state') on a specific resource, and adds what the agent gets from it: video path, transcript status, clip suggestions, settings, and workflow next steps. This clearly separates it from siblings like job_status and ai_cli_status, which monitor jobs/CLI health rather than session state plus guidance.

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 explicit timing guidance ('Call this FIRST when starting a new conversation to understand the current state') and explains the clip-numbering convention that feeds into create_clip, batch_create_clips, modify_clip, and toggle_clip. It doesn't explicitly name alternatives to avoid, but the first-call guidance plus the workflow-routing note is strong and actionable.

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