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

Annotations already cover safety (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower. The description adds real value by disclosing what the tool computes and returns (risk level, factors, recent board events), which goes beyond the annotation layer.

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?

Three tight sentences, front-loaded with the resource and its scope, followed by the model components and return contents. No filler; every sentence adds discriminating information.

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?

An output schema exists, so explaining return values in depth isn't required, and the description still names the key outputs. The only minor gap is that it says nothing about data freshness or the ticker scope, but for a single-param read tool this is essentially complete.

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?

With a single parameter at 100% schema description coverage ('NZX ticker symbol (e.g. "FPH", "AIR", "SPK")'), the schema already carries full parameter meaning. The description adds nothing about ticker format or constraints, so the baseline 3 applies.

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 verb and resource ('Get governance deterioration signal') and then enumerates the concrete 5-factor model it computes (GRS level, board stability, independence erosion, audit & risk flags, attendance). The concept of a 'deterioration' signal is clearly distinct from the many sibling governance-score tools, so an agent can tell what this returns without opening the schema.

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?

Explicitly states the use case: 'Use when assessing whether a company's governance is in decline.' This gives clear context, but it does not name alternatives or exclusions (e.g. get_governance_scores vs get_board_health_score) for when a static score is wanted rather than a decline signal.

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