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

Even though annotations already mark it read-only and idempotent, the description adds meaningful context: page size cap of 20, preservation of missing periods/currency/source dates, and the disabled mode with AUTH_REQUIRED failures. No contradiction with the annotations.

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 purpose and stays compact. 'Mode: disabled' and 'Research is disabled' are mildly redundant, but the information density is high and every sentence contributes.

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 read-only tool with an output schema and robust annotations, the description covers purpose, filter, pagination, and the current auth/disabled state. It is sufficient for an agent to understand the call and its constraints, though it does not suggest alternative tools.

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 documents query and symbol; the description adds that filtering is by label/ID and that pages hold up to 20 records, giving page some extra context. It does not deeply explain page-number semantics, so it adds only moderate value beyond the schema.

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 ('Read key statistics for a confirmed symbol') and adds the label/ID filter, clearly identifying the operation. It does not explicitly contrast with sibling tools, but the resource and filter are distinct enough to avoid major ambiguity.

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?

'Confirmed symbol' implies a prerequisite and gives an implied use case, and the disabled-mode warning tells the agent that calls will fail with AUTH_REQUIRED. There is no explicit when-to-use versus search_companies or list_metrics, so it stops short of clear routing guidance.

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

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

The description goes well beyond the readOnly/idempotent annotations by stating 'Mode: disabled' and 'calls return AUTH_REQUIRED without retrieving data,' which is critical for an agent deciding whether/how to invoke it. It also discloses that IDs are namespaced per service and must not be merged. No annotation contradiction.

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 tool's purpose is front-loaded and every sentence carries information. The disabled/research sentences are slightly choppy and redundant ('Mode: disabled' plus 'Research is disabled'), but the description remains efficiently packaged.

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 simple metadata-listing tool, the description covers purpose, symbol semantics, ID namespacing, and auth failure behavior, with an output schema covering return shape. The gap is that the valid namespace enum contradicts the broader service list in the description, which an agent would need clarified to call the tool 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?

With schema coverage at 50%, the description compensates partially by explaining symbol=null for market-wide services and by stressing service-namespaced IDs. But it references service names absent from the namespace enum and stays silent on page semantics, so the added value is real but imperfect.

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 opening sentence states a specific action and resource: 'Discover metric metadata without numeric values,' which clearly differentiates it from a numeric statistics tool like get_key_statistics. However, the description then lists financials, fundachart, and comparison as supported service scopes even though the namespace enum only allows keystats and screener, so the scope is slightly muddled.

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 useful context for when to pass a symbol vs null ('keystats and financials require a symbol; screener, fundachart and comparison are market-wide'), and it notes the tool is disabled with calls returning AUTH_REQUIRED. It never explicitly contrasts this tool with its siblings search_companies or get_key_statistics, nor says when to prefer another tool.

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

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

Annotations already mark the call as read-only, open-world, and idempotent, and the description adds meaningful behavioral detail: it excludes warrants, preserves multiple candidate matches, requires confirmation before fetching statistics, and discloses that calls currently return AUTH_REQUIRED without retrieving data. No contradiction with annotations exists.

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 concise and front-loaded with the core search purpose, followed by important exclusions and disabled-state warning. Minor redundancy exists between 'Mode: disabled' and 'Research is disabled,' but overall every sentence adds useful 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?

Given the simple one-parameter schema, the presence of an output schema, and rich annotations, the description is complete enough for an agent to call or avoid the tool correctly. It covers what is searched, what is excluded, the candidate behavior, the need for confirmation, and the current AUTH_REQUIRED failure mode.

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 0%, so the description must explain the query parameter. It does so by stating the query can be a 'symbol or company name' and clarifies that multiple candidates may be preserved. It does not give examples or case-format details, but for a single parameter this is adequate compensation.

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 uses a specific verb and resource: 'Search IDX equities by symbol or company name.' It further distinguishes the tool by noting it 'Excludes warrants' and 'preserves multiple candidates,' and its role is clearly positioned as a lookup step before fetching statistics. This separates it from sibling tools like list_metrics and get_key_statistics.

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 phrase 'Confirm the company before fetching statistics' explicitly places this tool before downstream statistics tools, giving an agent a clear workflow cue. It also warns that 'Research is disabled; calls return AUTH_REQUIRED without retrieving data,' which tells the agent when the tool will not be usable. It does not explicitly name alternatives, but the workflow context is sufficient.

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