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

Annotations already declare readOnly/idempotent/non-destructive, so the bar for added behavioral context is lower. The description adds meaningful behavior: it returns a unified cross-market stream, can combine multiple signal types, and includes composite signals that detect patterns like insider selling plus earnings miss. It also clarifies the feed's broad scope, which is not inferable from the schema alone.

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 front-loaded with the core definition and scope, then gives compact example queries and routing. It is longer than average, but the length is justified by the large palette of signal types and the need to distinguish siblings. The final caution about routing is somewhat redundant with the earlier routing statement but earns its place by preventing misuse.

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 six-parameter, no-required-parameter tool with an output schema, the description plus schema covers what an agent needs: purpose, scope, routing, parameter semantics, and return coverage via the output schema. It explicitly handles the common confusion with sibling tools and provides example invocations. No critical behavior or parameter concern is left unaddressed.

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 description coverage is 100% and each parameter (days, type, limit, sector, ticker, significance) already has a semantic description with defaults and examples. The tool description doesn't need to repeat parameter details, so the baseline of 3 applies. It does reinforce the available signal type vocabulary informally, but the schema already lists the exact underscore codes.

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 specific verb and resource ('Get the Market Intelligence Feed') and immediately defines its scope as a unified stream of all NZX market events. It differentiates itself from sibling tools by explicitly stating it is the cross-market feed and by naming the specific single-dataset tools it is not. The enumeration of 13 signal types leaves no ambiguity about what the tool covers.

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?

Contains explicit routing guidance: use it for 'what is happening across the market' or when scanning several signal types at once, and avoid it for a question about one dataset for one company. It names the preferred sibling tools for single-dataset queries (get_capital_raises, get_agm_resolutions, etc.) and adds the warning that listing a signal type does not mean this is the best tool. Example phrasings ('what happened on the NZX today/this week?') anchor when to use it.

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