ticket_context

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

Annotations declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds meaningful behavioral detail beyond these annotations: it states the output is 'evidence, not prose', highlights that the file list is 'a search result, not an understanding of the code', and even notes it may include irrelevant matches ('things that merely share a word'). This transparently sets expectations about the tool's limitations and nature, which is exactly what the dimension asks for.

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 longer than average but well-structured with a clear instruction up front, followed by bullet points that add value. Every sentence serves a purpose: defining scope, explaining the return type, listing evidence types, and giving a caution. It is front-loaded with the core directive and does not waste words, so the length is justified.

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 tool that searches across tickets, MRs, and checkout files, the description covers what the tool returns, the caveats, and the recommended usage flow. An output schema exists, so the return structure is likely defined there; the description doesn't need to repeat it. The only missing element is a concrete note on parameter syntax or edge cases, but given the output schema and the detailed behavioral notes, the description is sufficiently complete for an agent to call it correctly.

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?

The input schema provides no descriptions for its parameters and the schema_description_coverage is 0%. The description mentions 'subject' implicitly in the purpose line ('a subject') but does not explain how to use `repo`, `project`, or `tracker`. With zero schema coverage, the description needed to compensate by clarifying these parameters, but it does not. The agent is left to guess what each parameter means, making this a notable 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 opens with a clear, specific directive: 'Gather what is known about a subject before you write the ticket for it.' It explicitly lists what it returns (evidence, past tickets, files changed, file mentions) and contrasts it with prose. It also names the sibling `ticket_template` and positions itself as complementary, making the tool's distinct role immediately apparent.

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 gives an explicit, actionable workflow: 'Call this together with `ticket_template`, then write the ticket yourself.' It further instructs the agent to 'Read the files it points at before drafting' and warns against treating the list as understanding. This leaves no ambiguity about when and how to invoke the tool relative to the ticket-writing pipeline.

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