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, yet it only implies a mutation. It says nothing about permissions required, whether the dispute is reversible, whether the original record content is preserved, or how the disputed state differs from deletion.

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 tight sentence with the action front-loaded and the qualifying condition appended. No filler, nothing 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 values need no explanation, but for a state-mutating tool with no annotations the description should cover reversibility and required identifiers. It covers the conceptual trigger well while leaving operational details thin.

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 two required parameters, and the description never mentions record_id or project_path. It adds no meaning beyond the raw parameter names, leaving the agent to guess formats and scoping.

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 ("mark a record disputed") plus the triggering condition ("evidence conflicts but no replacement is established"). This implicitly separates it from supersede_memory, which presumably applies when a replacement exists, 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?

Gives a clear when-to-use condition tied to the state of the evidence. It stops short of explicitly naming the alternative (supersede_memory) or stating when not to use it, so the routing is inferable but not spelled out.

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 only partially does so: it discloses the meaningful inheritance behavior (parent-directory rules are included) and that rules are filtered to 'active'. It says nothing about auth needs, response shape, or how 'active' is determined, leaving real gaps.

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 tight sentence with the core purpose front-loaded and no filler. It is efficient, though its brevity contributes to the coverage gaps elsewhere.

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, but a 3-parameter read tool with no annotations and 0% schema coverage needs more than one sentence. The limit/pagination behavior and the interaction between project_path and paths are left entirely 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 the description compensates only weakly: 'files' loosely implies the paths parameter, but project_path and limit are never addressed. Two of three parameters, including the pagination control, remain semantically opaque.

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 ('active rules for files'), and adds a scope qualifier ('including rules attached to their parent directories'). It is distinguishable from the memory-oriented siblings, but it never names them to sharpen the contrast.

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 guidance, no prerequisites, and no mention of alternatives among search_memory/record_memory/supersede_memory/dispute_memory. Usage is only implied by the word 'Get'.

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 signals durability and optional file/directory scoping, but says nothing about how records interact with existing entries, what authority levels imply, whether entries can be edited, or any auth constraints on a mutation 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?

A single front-loaded sentence with no filler, and the optional-scope clause is placed sensibly at the end. It is efficient, though arguably too terse for an 8-parameter mutation tool.

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, but for a write tool with 8 parameters, 5 required, 0% schema coverage, and zero annotations, the description is far too thin to let an agent call this 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% across 8 parameters, and the description only alludes to one of them (applies_to, via 'project-relative files or directories'). The critical enum fields kind and authority, plus title, content, tags, source, and project_path, receive no explanatory text anywhere.

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 (record) and resource (durable knowledge) and adds a scoping qualifier. It implicitly distinguishes itself from search_memory and the dispute/supersede siblings by being the write path, but it never names those alternatives.

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 record versus when to use supersede_memory or dispute_memory, nor any stated preconditions. The agent must infer usage entirely from the verb.

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 and discloses almost nothing: no permission requirements, no result ordering, no pagination behavior despite a limit param, and no note that inactive memories are excluded by default (include_inactive=false). It is a read-style search, but that must be inferred from the verb alone.

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 padding that leads with the query modes. It is efficient, though arguably too terse for a 5-parameter tool with no other documentation.

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, but the description still omits behavior an agent needs: the default exclusion of inactive memories, how limit affects results, and how tags and phrase combine when both are supplied. For a search tool with five params and zero schema coverage, this is a meaningful gap.

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 5 parameters, so the description must compensate and only partially does: it clarifies that tags should be 'exact' and limited to 1-3, and that phrase is free-text, which adds real meaning. But limit, project_path, and especially include_inactive (whose default silently drops inactive memories) are left entirely unexplained.

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 clear verb (search) and the two input modes it accepts (1-3 exact tags, broad free-text phrase, or both), which is specific enough for an agent to know what the tool retrieves. It does not distinguish itself from siblings like get_file_context, which could also surface related content, so it stops 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?

The description says how to query but never when to choose this tool over get_file_context, nor any exclusion or precondition. The only implied guidance is the tag-vs-phrase dichotomy, which is a mechanics hint rather than usage routing.

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 for a mutating tool. It does not say whether superseding is reversible, whether the record is archived or deleted, what permissions are needed, or what happens if the record is already superseded; only the optional replacement link is disclosed.

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; the core action is stated first and the optional linkage second.

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 no explanation, but for a state-changing tool with no annotations the description should have covered irreversibility, permissions, or the effect on the linked replacement. It remains minimally adequate rather than complete.

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. It does clarify the meaning and optionality of replacement_id ('optionally linking its active replacement'), which is the least self-evident parameter, but project_path and record_id receive no explanation beyond their names.

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-plus-resource ('mark obsolete memory superseded') that is readily distinguishable from siblings like record_memory, search_memory, and dispute_memory. It also names the key side effect (linking a replacement), though it does not explicitly contrast itself with dispute_memory.

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 by the word 'obsolete' — the agent infers this is for records that are no longer current — but there is no explicit when/when-not guidance or routing between this and dispute_memory, which is a natural alternative for contested records.

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