pr_guide

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

With no annotations, the description must carry the behavioral burden. It does disclose that content comes from plain .md files with no build step and that the tool has a listing mode versus a read mode, but it says nothing about what a read returns, what happens when a topic name is invalid, or whether listing and reading differ in cost.

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 useful guidance (modes, content domains, read-before-choosing) is present, but the parenthetical about dropping .md files into the Premiere/Kiến thức folder with no build is maintainer-facing noise, and the dense run-on content list makes it harder to scan. Trimming the authoring detail would sharpen it.

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 single-optional-parameter, read-only docs tool with no output schema and no annotations, the description covers what the tool is, how to invoke both modes, and when to consult it. The main missing piece is output shape per mode, which is low-stakes for a markdown reader.

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 documents that topic is the file name without .md and that omitting it lists, so the baseline is 3. The description adds real value on top by describing the discovery loop — list first, then read by name — which tells the agent how to obtain a valid topic value.

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 plainly establishes this as a Premiere knowledge-base reader and enumerates the content domains it covers (transitions and when to use them, MCP-drivable vs manual plugins, export rules), plus the two call modes. It is clearly not a sibling tool, though it does not explicitly distinguish itself from domain-overlapping siblings like list_available_transitions or list_available_effects, which also answer 'which transitions exist'.

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?

"Call with no topic to list topics, then with a topic name to read it" gives an explicit two-step procedure, and "Read it before choosing transitions or plugins" states a triggering condition. It stops short of saying when not to use it, or why an agent would pick this over the live list_available_transitions/list_available_effects tools.

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