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

Annotations declare readOnlyHint=false and destructiveHint=true, while the description describes a search/read operation with no mention of side effects. This is a contradiction the description does not resolve, so an agent could be misled about safety. The description does add useful behavioral details (no pagination, all companies returned, date-range precedence, available markets), but the contradiction is a serious flaw.

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 long but well-structured with <strategy> and <critical_rules> blocks. It front-loads the purpose and organizes parameter rules clearly. Every sentence adds value, though it could be trimmed slightly without losing meaning.

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?

Given the lack of an output schema, the description does well to explain what is returned (all matching companies, no pagination, grouped by stock_code, with latest publish_date and report types). It covers key usage constraints and data availability. The main gap is the unresolved contradiction with annotations.

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%, giving a baseline of 3, but the description adds substantial meaning beyond the schema: it explains precedence of startDate/endDate over days, auto-fill behavior, default/max of days, requirement of at least one date parameter, date format, market values, and reportType examples. This goes well beyond the schema's descriptions.

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 states a specific verb ('search') and resource ('companies by financial report publish date'). It distinguishes from siblings by explicitly naming financialKeywordSearch and getFinancialReportPages as follow-up tools for reading actual report content, and the scope (publish date) is clear and differentiated.

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 <strategy> block explicitly tells when to use this tool: to find companies with reports published in a specific time window. It also provides next-step guidance (use financialKeywordSearch or getFinancialReportPages) and notes data availability for CN-A/HK, which helps an agent decide. It lacks a formal when-not list but effectively implies boundaries by naming alternatives.

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