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

With no annotations, the description carries the full burden. It usefully discloses the return content (columns plus foreign-key relationships), which matters since there is no output schema, but it says nothing about error behavior for missing tables, required database context, or read-only nature.

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?

A single front-loaded sentence with zero filler; every clause earns its place by naming the resource and the two things returned.

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 one-parameter read-only introspection tool with no output schema, the description covers what is returned and what identifier is accepted. Minor gaps remain around qualification of the table name and error handling.

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 single parameter 'table' has 0% schema description coverage, so the schema gives no help. The description partially compensates by indicating the parameter accepts a table or view name, which is genuine added semantics, but it omits whether the name must be schema/database qualified.

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 (describe) and resource (columns and foreign-key relationships for one table or view), which is clearly distinct from sibling tools like mysql_list_indexes or mysql_list_tables. It does not, however, explicitly contrast itself with those siblings, so it falls just short of the 5 bar.

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?

There is no when-to-use or when-not-to-use guidance, and no naming of alternatives such as mysql_query or mysql_list_indexes. The purpose hints at schema-introspection usage, but no explicit guidance is offered.

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?

With no annotations, the description carries the full burden, and it does disclose that only read-only SELECT input is accepted, implying safety and rejection of other statement types. It omits whether the query is ever executed, what happens on non-SELECT input, and required privileges.

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?

One sentence, no waste, with the return type and the input constraint front-loaded. Every clause earns its place.

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?

The return value (JSON execution plan) is stated, which matters since no output schema exists, and the single parameter's constraint is given. Still missing is guidance on choosing this over mysql_query and any note on how the plan is produced (plain EXPLAIN vs execution).

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 0% and the lone parameter 'sql' is undescribed in the schema, so the description must compensate. It adds that the value must be a read-only SELECT, which is useful, but says nothing about formatting, placeholders, or statement termination.

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 ('Return') and resource ('JSON execution plan'), plus the accepted input type ('safe read-only SELECT query'). It does not differentiate from siblings like mysql_query, which an agent might otherwise pick to run the same SQL.

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?

Usage is implied: reach for this when you want a plan rather than results. There is no explicit statement of when to prefer mysql_explain over mysql_query, nor any prerequisite or exclusion noted.

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?

No annotations are provided, so the description must disclose behavioral traits. The verb 'Return' implies a read-only, side-effect-free operation, but the description does not explicitly confirm this, nor does it mention authentication requirements, rate limits, or whether any server state is affected.

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?

A single, front-loaded sentence that lists the returned fields without waste. Every element earns its place.

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 no-argument read tool with no output schema, the description enumerates the key return values (database, version, charset, timezone, safety limits), which is sufficient for an agent to understand the tool's output. It could additionally state that no arguments are needed, but the schema already conveys that.

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 zero parameters and complete schema coverage, the description need not discuss parameters. The baseline of 4 applies because no parameter information is missing.

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 ('Return') and enumerates the exact server-level resources (database, version, charset, timezone, safety limits). This clearly differentiates it from sibling tools that deal with tables, indexes, queries, or execution plans, though no sibling is named explicitly.

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?

Provides no guidance on when to call this tool versus alternatives, no prerequisites, and no exclusions. It only describes what the tool returns, leaving the agent to infer that it is used for server configuration inspection.

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?

No annotations are provided, so the description carries full behavioral burden. It conveys read-only intent implicitly via 'List' but does not state that this is a read operation, whether it requires database selection, or what happens on a missing table.

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?

Single sentence, front-loaded verb, zero wasted words.

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 single-param read tool with no output schema, the description adequately conveys purpose but lacks the behavioral context (read-only nature, auth/db prerequisites) an agent would benefit from given no 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?

Only one parameter with 0% schema description coverage. The description names the scope ('one table') which maps to the single table param, but adds no syntax or format detail; with 0 params this baseline would be higher, but the param is undocumented.

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 (List) and resource (indexes and ordered indexed columns) scoped to one table, which cleanly distinguishes it from siblings like mysql_describe_table and mysql_list_tables.

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 'for one table' scoping implies this is the index-inspection tool versus describe_table for columns, but no explicit when/when-not guidance or named alternatives are given.

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?

With no annotations provided, the description carries the full burden, yet it says nothing about read-only safety, default pagination (limit defaults to 50), or the fact that results may be truncated at 200. For a listing tool whose output can be silently bounded, that omission matters.

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?

A single front-loaded sentence with no filler or repetition. It is tight and immediately readable, which is the one dimension where this definition performs well.

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 tool with three undocumented parameters, no annotations, and no output schema, one sentence is not enough. Pagination behavior, filtering, and the shape of the returned list are all left to inference.

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% across three parameters, and the description does not mention limit, offset, or keyword at all. The keyword filter in particular is entirely undiscoverable from the definition text, so an agent may never learn it can filter results.

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 ('List') and resource ('tables and views') with scope ('in the configured database'). It is distinguishable from mysql_describe_table and mysql_list_indexes, but it never explicitly names those siblings or contrasts its role with them.

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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as mysql_describe_table or mysql_query. The agent must infer from the name alone that this is the discovery step before describing or querying a table.

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?

With no annotations, the description carries the full burden; it does disclose that execution is read-only and limited to a single statement ('one safe'), which is real behavioral value. It omits row limits, timeouts, permission requirements, and error behavior for rejected SQL.

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?

A single front-loaded sentence with no waste; the read-only restriction appears immediately after the verb. The adjective 'safe' adds little beyond 'read-only', a minor redundancy.

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?

There is no output schema and no annotations, so the description must cover everything. It establishes the read-only contract but leaves return shape (result rows), limits, and failure modes unspecified, which is a meaningful gap for an arbitrary-SQL tool.

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% for the single 'sql' parameter, so the description must compensate. It adds the useful constraint that the SQL must be a SELECT or read-only CTE, but says nothing about quoting, trailing semicolons, multi-statement rejection, or placeholders.

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 (execute) plus the resource and scope (SELECT / read-only CTE against the configured database). This cleanly separates it from the metadata siblings (list_tables, describe_table, list_indexes), though it never names them explicitly.

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 read-only constraint is stated, which implicitly tells an agent when this tool is valid, but there is no explicit when-to-use guidance and no routing to siblings such as mysql_explain for plan inspection. Usage must be inferred from the constraint alone.

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