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

The description adds valuable behavioral context beyond the annotations: it notes the search covers 2017-present, that most announcements have extracted PDF text (implying some may not be searchable), and that certain AI fields like ai_sentiment are optional ('May also include'). This discloses variability in results and search coverage. It does not contradict any annotations, and the readOnlyHint is consistent with a search operation.

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 well-structured and front-loaded: it starts with the core function and scope, then provides usage guidance, and finally enumerates the AI-annotated result fields. It is slightly longer than necessary but every sentence conveys relevant information, and it avoids redundancy with the schema. The organization makes it easy for an agent to quickly grasp the tool's purpose and expected outputs.

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 search tool with six optional parameters and an output schema (which exists but isn't shown), the description covers the key contextual aspects: search scope, date range, and the variety of AI fields returned. It explains that some fields are conditional ('May also include'), which is important for interpreting results. While it doesn't address pagination or error handling, the presence of an output schema reduces the burden on the description, and the overall coverage is sufficient for correct invocation.

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 schema already provides complete descriptions for all six parameters (100% coverage), including details like 'searches both titles and full PDF document text' for the query parameter. The tool description itself does not add further parameter-specific semantics beyond what the schema already states. With full schema coverage, a baseline of 3 is appropriate; the description's focus on result fields is useful context but does not enhance parameter understanding.

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 clearly states the tool performs full-text search across NZX market announcements, specifically searching both titles and full document content. It distinguishes itself from siblings like read_announcement (fetching a specific announcement) and search_companies (searching companies) by emphasizing cross-filing content search. The date range and AI classification outputs further clarify its unique role.

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?

It explicitly states the intended use: 'Use for finding mentions of specific topics, companies, people, or events across all NZX filings.' This gives clear context, though it doesn't explicitly state when NOT to use it or mention alternative tools. The guidance is strong but could be more explicit about exclusions, such as not using it for fetching a single known announcement.

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