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 a good deal: the tool is a retrieval/consultation operation whose output comprises rules, specs, traps, and verified code patterns. It omits operational traits like permissions, caching, or whether results are scoped/paginated, but the read-only nature is unambiguous from the 'Returns:' framing.

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?

Front-loaded with the mandatory pre-flight directive, followed by a scannable Returns list and Args block. Efficient overall, though the Returns bullets partially duplicate what the output schema already exposes, adding mild 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?

For a low-complexity two-parameter retrieval tool, the description is essentially complete: it conveys purpose, trigger, output categories, and both parameters. The presence of an output schema makes the Returns list somewhat redundant, but nothing an agent needs to invoke it correctly 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 description coverage is 0%, so the description must compensate — and it does, documenting both parameters: 'context' as the topic/stack/task with concrete examples ('php mysql pdo', 'authentication'), and 'project' as a name/slug with the 'global' fallback. It adds real meaning beyond the bare schema titles.

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 (consult) and enumerates exactly what it retrieves: active project rules, prerequisite specs, known AI blind spots, and golden patterns. This clearly distinguishes it from the sibling write/list tools (brain_record_rule, brain_list_rules, brain_stats), which merely record or enumerate rather than synthesize guidance.

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 frames when to call it: 'Call this before writing, designing, or refactoring code' — a concrete trigger condition. It does not, however, name alternatives or state when NOT to use it, so it falls short of the full when/when-not/alternatives bar.

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 does disclose two useful traits — only *active* rules are returned and global rules are always merged into the result — but it does not state the read-only nature explicitly, nor anything about ordering, volume, or pagination.

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 well-formed sentence with the scope front-loaded and zero filler. Nothing in it is redundant.

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 return-value detail is not needed, and the scope sentence covers the main ambiguity about global rules. The remaining gap is the absence of any usage/routing guidance for a tool sitting among six siblings.

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?

There is one parameter with 0% schema description coverage, so the schema explains nothing. The description adds partial meaning by framing the parameter as the project scope and clarifying that global rules are included regardless, but it does not explain the 'global' default or what happens when the argument 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?

The description gives a specific verb (List) and resource (rules) plus the scope (active rules for the given project, including global rules). It is clearly distinguishable from the write-side siblings like brain_record_rule, though it never names an alternative tool 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?

There is no guidance on when to call this versus siblings such as brain_consult or brain_stats, and no stated prerequisites or exclusions. Usage is only implied by the verb 'List'.

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 implies persistence-for-future-use via the 'vaccinate' framing, but never states that the record is stored, later surfaced by brain_consult, deduplicated, or that it is an irreversible write; no auth, confirmation, or rate-limit context is given.

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 trigger condition is front-loaded in one sentence, then a compact Args block; every line earns its place. The all-caps 'VACCINATE AGAINST MISTAKES' opener is rhetorical rather than informative, a minor style cost.

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 5-param write tool with an output schema, the description covers triggers and all parameters adequately. The remaining gap is relational: verified_snippet 'also saves a Golden Pattern' overlaps with the brain_record_golden_pattern sibling, and the description never resolves which tool an agent should pick.

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 carry all parameter meaning, and it does: it explains each of the five arguments, gives concrete context examples ('php mysql utf8mb4', 'docker windows networking'), defines project as an identifier or 'global' (matching the default), and marks verified_snippet optional while noting its dual role as a Golden Pattern.

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 concrete verb+resource (record an experience) and enumerates the triggering situations: >=2 attempts fixing an error, an unexpected runtime pitfall, or the user saying 'grava isso'/'aprende isso'. It is clearly distinguishable from brain_list_rules or brain_stats, though the overlap with brain_record_golden_pattern is only hinted at rather than stated.

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?

Strong explicit trigger conditions ('Call this whenever you spent >= 2 attempts...') give an agent a clear activation rule. It does not state when NOT to use it, nor explicitly route between the near-siblings brain_record_rule and brain_record_golden_pattern, even though the verified_snippet argument touches the latter's territory.

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 the full behavioral burden. It says the snippet must be 'exact verified working code' but never states whether re-recording the same title overwrites or duplicates, how patterns are later retrieved, or any permission/scope requirements for a write operation.

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?

Front-loaded with a single high-signal sentence, followed by a tight Args list with no filler. It is appropriately sized for a five-parameter tool, though the Args glosses are thin relative to the space they occupy.

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 return values need not be described. The remaining gap is behavioral: for a persistence tool with no annotations, the description says nothing about storage scope, overwrite semantics, or how the recorded pattern is subsequently surfaced to agents.

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 compensate, and the Args block does enumerate all five parameters. However most glosses merely restate the field names ('title: Short descriptive title', 'code_snippet: The exact verified working code'); only the context example ('php mysql pdo') and the 'global' project default add real semantic value.

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 first sentence gives a specific verb+resource: saving a 'battle-tested code snippet' as a reusable 'golden pattern'. It implies a distinct artifact type versus siblings like brain_record_experience or brain_record_rule, but never names or contrasts them, so the differentiation is inferential rather than explicit.

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?

"agents must copy/adopt instead of reinventing boilerplate" hints at the trigger condition (you have verified boilerplate worth reusing), but there is no explicit when-to-use/when-not guidance and no routing to brain_record_experience or brain_record_rule for non-code knowledge.

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 the full burden. It implies the rule persists and is obeyed by agents ('must always obey'), but says nothing about storage scope, whether rules are ever deleted or superseded, permission requirements, or what happens if a conflicting rule exists. For a mutation tool with zero annotation coverage this is a significant gap.

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 states the tool's effect, followed by a compact Args list. The parameter names repeat the schema keys, but the examples and severity enumeration earn their space, so there is little waste.

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 return values need not be explained. However, for an unannotated mutation tool the description leaves the agent without the persistence and conflict semantics it would need to call this confidently alongside brain_list_rules and brain_record_experience.

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 compensate, and it largely does: it defines all four parameters, gives a concrete example for 'rule', lists candidate categories, explains that 'project' accepts an identifier or 'global', and enumerates the four valid severity values even though the schema declares no enum. It stops short of explaining default behavior (e.g., what 'global' scope means in practice).

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 gives a clear verb and resource ('Enforce a strict constraint') that maps to the tool name brain_record_rule, and the Args block confirms the recorded entity is a rule. It does not differentiate from siblings like brain_record_experience or brain_record_golden_pattern, which also record persistent agent knowledge, so an agent must infer the distinction from names alone.

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 record a rule versus the sibling tools, no preconditions, and no exclusions. The only usage signal is the adjective 'strict', which hints at durable/high-importance content but is not an actionable routing condition.

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 does disclose the key trait - the registration creates a mandatory read requirement ('MUST read') rather than an advisory note - but says nothing about persistence scope, whether re-registering the same spec_path overwrites, how trigger matching is evaluated, or permission needs.

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?

Front-loaded one-sentence purpose followed by a compact per-parameter list; no filler. The docstring formatting ('Args:') is slightly mechanical but every line carries usable 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 return values need not be explained, and all four params are documented. However, with no annotations and several sibling rule-recording tools, the description leaves unaddressed how this requirement persists and how it interacts with brain_record_rule, which an agent needs in order to choose 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?

Schema description coverage is 0%, so the description must compensate, and the Args block documents all four parameters with concrete examples ('design, ui, layout, componentes') and the intended value of project. It does not state that project defaults to 'global' explicitly, leaving that to 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?

States a specific verb and resource ('Register a specification file') plus the distinguishing behavioral property that the agent MUST read it before matching topics. This separates it from siblings like brain_record_rule and brain_record_golden_pattern, though it never names those alternatives 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 'MUST read before working on matching topics' clause implies when the tool is appropriate, but there is no explicit when-to-use/when-not guidance and no comparison to brain_record_rule or brain_record_golden_pattern, which an agent could easily confuse with this 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?

No annotations provided, so the description carries the full burden. 'Get' implies a read operation and 'current' implies a snapshot, but it doesn't state whether it requires auth, what statistics are returned, or whether it's expensive. Has an output schema which covers returns, lowering the burden somewhat.

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 short sentence, front-loaded with the action. Appropriate size for a no-param tool, though slightly terse on detail.

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?

Output schema exists so return values needn't be explained, and there are no params. But a no-annotation read tool with ambiguous statistics scope and no usage guidance leaves some gaps for an agent deciding when to call it versus brain_consult.

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?

Zero parameters, so baseline 4 applies. No parameter semantics to add.

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 (Get) and resource (knowledge base statistics) with clear scope. It is distinguishable from siblings like brain_consult and brain_record_* which are query/write operations, though the description doesn't explicitly differentiate.

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?

Only 'Get current knowledge base statistics' with no indication of when to use this versus brain_consult or brain_list_rules. No usage context, prerequisites, or alternatives named.

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