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

No annotations are provided, so the description carries the full behavioral burden. It hints that the output includes a 'safe example,' but does not state that this is a read-only lookup, whether authentication is required, or what happens with invalid rule IDs.

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 a single front-loaded sentence with no wasted words. It efficiently states the action and expected output shape.

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 tool with no annotations and no output schema, the description leaves important gaps: valid rule ID format, whether the operation is read-only, and error behavior are all unspecified. It is usable but not complete enough for confident invocation.

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 single parameter. It gives only an example value ('L02') and does not specify format, valid range, or where rule IDs come from.

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 and resource: 'Explain one rule,' and adds the intended content ('why it matters and a safe example'). It implicitly distinguishes from the sibling 'list_rules' by emphasizing one rule, but does not explicitly contrast with it.

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 explicit guidance on when to use this tool versus 'list_rules' or the review tools. Usage is only implied by the word 'Explain' and the example rule ID.

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 exist, so the description must carry the behavioral burden; 'list' implies a non-mutating read and 'every rule' implies full enumeration rather than pagination, which is useful. However, it says nothing about ordering, whether custom or server-default rules are both included, or any auth/scope requirements for a tool with zero annotation coverage.

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 sentence with no filler, front-loaded on the action and followed immediately by the payload the caller receives. 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?

For a zero-parameter, read-only enumeration with an output schema that already documents the return shape, the description covers the essentials. Minor gaps remain around scope (all rules vs. configured rules) and ordering, which matter for a rule catalog an agent will index into.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly frames the call as taking no filtering arguments, consistent with the empty 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?

States a specific verb and resource ('List every rule this server checks') and even previews the returned fields (id, title, default severity), so the agent knows exactly what comes back. It does not explicitly contrast itself with the sibling explain_rule, which is the obvious adjacency, so it falls short of a 5.

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 only implied: an agent can infer this is the discovery step before calling explain_rule or any review_* tool, but the description never says so. There is no when-to-use/when-not statement and no named alternative, leaving routing between list_rules and explain_rule to inference.

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 exist, so the description carries the full burden and does so well: it discloses that it does not touch the database, that checks are for the primary, and that each query returns rows only when the deploy should wait, which tells the agent how to interpret empty results. It stops short of stating the tool is read-only/non-destructive with no side effects and says nothing about the volume or length of the generated 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?

The core behavior and the 'does not connect' caveat are front-loaded, followed by a compact Args block. Every sentence carries information the agent needs; nothing repeats the schema or the name.

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?

With no annotations and no output schema, this is a high-complexity tool and the description covers what an agent must know: what it produces, that it must be relayed to the user, what the returned rows mean, and how the optional version parameter changes output. Nothing required for correct invocation is missing.

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%, so the description must compensate and largely does: it explains that `sql` is the migration about to run and that `mysql_version` is optional server version, with a concrete example ('5.7.44') and its observable effect (picks SHOW SLAVE vs REPLICA STATUS). It could still say what happens when mysql_version is omitted.

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 resource (SQL for pre-deploy checks) with a specific scope: long transactions, long queries, metadata locks on touched tables, table sizes, replica lag. The line 'This tool does not connect to the database; hand the SQL to the user' resolves the biggest ambiguity an agent would have (execute vs. emit) and cleanly separates it from review_migration, which presumably analyzes rather than generates diagnostic 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?

Timing is explicit ('right before deploying a migration'), which is a real usage condition rather than a vague hint. It lacks an explicit exclusion or a named alternative for adjacent needs (e.g. 'for static analysis of the migration, use review_migration'), so it falls short of a 5.

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 the return shape: a verdict (safe / block) plus findings with line numbers and a parameterized fix. That is meaningful beyond structured data since no output schema exists. It does not state that this is static analysis without execution, whether it reads any files from disk, or any size/rate limits.

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?

Two short sentences, zero filler: the check is front-loaded, then the return contract. Nothing is repeated from the name or title.

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 tool with no annotations and no output schema, the description covers purpose, supported languages, and return shape adequately. The remaining gap is scope transparency — what the `code` input should contain and the limits of the static analysis.

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%, so the single required `code` parameter is undocumented in the schema; the description only indirectly informs it by listing supported languages. It adds no guidance on whether the value is a full file, a snippet, or whether multiple files can be concatenated.

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 names a specific verb (check/review), a specific resource (application source code, with the languages enumerated), and the exact defect class it looks for (SQL built by string interpolation or concatenation). The 'application source code' framing also implicitly separates it from review_query and review_migration, which operate on SQL artifacts rather than host-language code.

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 statement of when to use this versus review_query, review_migration, or preflight_checks, and no when-not guidance. It also doesn't say whether to pass an entire file, a snippet, or a multi-file selection, which is the main usage decision an agent faces.

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 exist, so the description carries the burden and does substantial work: it discloses the return shape (verdict of safe/review/block with findings containing line, impact, fix) and a key hidden assumption ('Without it, 8.0.29 or later is assumed'), which materially affects verdicts. It does not explicitly state that nothing is executed against the server or what access/permissions it needs, leaving one notable gap for a no-annotation tool.

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 purpose and return contract are front-loaded in a single sentence, followed by a dense per-argument block where every line adds information an agent would otherwise have to guess. No filler or restatement of the tool name.

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 analysis tool with no annotations and no output schema, the description covers inputs thoroughly, states the verdict vocabulary, and documents a default assumption. Only the execution/safety model (does it touch the target server, what connection or credentials it uses) is left implicit.

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% and all six parameters carry only bare titles, so the description must compensate — and it does. It gives the exact JSON shape for stats with a concrete example, version string examples including a vendor variant, the 1M rows / 5 GB threshold definition, the cross-parameter interaction between stats bytes and free_disk_gb, and where rollback comes from.

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 names a specific verb (review), a specific resource (MySQL DDL or migration script), and the exact risk classes examined (locking, data-loss, replication). The resource scope is distinct from siblings like review_query and review_code, so an agent can route correctly 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?

Usage context is clear from the risk framing — analyze a migration before running it — and each optional input is justified by what it enables ('Makes column-type and index checks exact', 'a table rebuild that does not fit is blocked'). There is no explicit exclusion or named alternative (e.g. when to prefer preflight_checks), which keeps it below a 5.

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 behavioral burden. It usefully discloses the checks performed and the return shape (verdict safe/review/block and findings with line, impact, fix), but it does not explicitly state that the tool is read-only, does not execute queries, or whether authentication/rate limits apply.

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, compact, and free of filler. It covers the core analysis scope and the return format in two short sentences.

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 description explains what the tool checks and what it returns, which is helpful given there is no output schema. But for a four-parameter tool with 0% schema description coverage and no annotations, it leaves important parameter and behavioral context undocumented.

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% and there are four parameters. The description only clarifies one parameter indirectly by saying to pass schema for index checks; it adds no semantics for stats or mysql_version and gives no format detail for sql beyond the query types.

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: review queries an application will run, including SELECT/UPDATE/DELETE/INSERT. It also names the checks performed, making the tool's role clear, though it does not explicitly contrast itself with siblings such as review_migration or review_code.

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 implies usage by saying it reviews queries an application will run and advises passing schema for index checks. However, it gives no explicit when-to-use guidance versus alternatives and no when-not-to-use or prerequisite context.

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