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

With no annotations, the description carries the burden alone; 'get' plus 'statistics' implies a safe read-only, zero-side-effect call, which is helpful. It also discloses the data is real-time, but says nothing about cost, auth, or whether the snapshot is expensive to compute.

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 resource and scope arrive immediately.

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 diagnostic call, the description conveys enough to invoke it correctly. Since there is no output schema, it partially compensates by naming the return content (statistics and node counts), though the exact metrics returned remain unspecified.

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. Baseline 4 applies for a parameterless tool.

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 (real-time statistics and node counts) scoped to the Synapse memory cortex. This clearly separates it from the sibling memory operations (recall, retain, record_episode), 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?

Usage is only implied: an agent can infer this is the tool for inspecting cortex health rather than reading or writing memories. There is no explicit statement of when to call it, when not to, or which sibling to prefer for adjacent needs.

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 usefully discloses the hybrid vector+BM25 retrieval mechanism and that results are bounded by a token budget, but it does not state that the operation is read-only/non-mutating, what the result structure or ranking looks like, or any permission requirements.

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 dense sentence with no filler, front-loading the action and the target resources before the retrieval mechanism. Every clause carries information an agent needs.

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 retrieval tool with no annotations and no output schema, the description explains what is searched and how, but leaves the return format and result characteristics (snippets, scores, ordering) unexplained. The omission is a meaningful gap for a recall tool whose output shape matters.

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 100%, so the schema already documents both parameters thoroughly, including the token budget default. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 is appropriate.

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 ('Recall') and concrete resource types (memories, SOPs, past architectural decisions), plus the retrieval mechanism. This clearly distinguishes it as the read-side counterpart to synapse_retain and synapse_record_episode, though it never names the siblings 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 description implies when to use it (retrieving prior context) but gives no explicit guidance on when to prefer it over synapse_get_stats or how it relates to the write-side siblings. Usage is inferable from the verb and resource list rather than stated.

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 discloses that this is a persistence operation, but says nothing about whether entries are deduplicated, embedded/indexed for later recall, mutable or overwritable, or what happens when salience is changed. The 'salience' impact factor behavior is also unexplained.

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 verb and resource lead and the rationale trails. Nothing is wasted.

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?

A six-parameter, five-required mutation with no annotations and no output schema needs more than one sentence. Nothing tells the agent what the call returns, whether the record is immediately recallable via synapse_recall, or how salience affects later retrieval.

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 100%, so all six parameters are already documented in the schema, establishing a baseline of 3. The description's 'Situation -> Action -> Outcome -> Lesson' framing only restates the parameter names in sequence and adds no format, length, or content guidance 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?

States a specific verb ('Record') and a specific resource ('episodic learning memory'), plus the narrative structure (Situation -> Action -> Outcome -> Lesson). It is clearly distinguishable from synapse_recall in intent, but it never names siblings or explicitly contrasts with synapse_retain, which is the closest functional neighbor.

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 clause 'so agents never repeat past mistakes' hints at motivation but gives no condition for when to call this versus synapse_retain (both are write-side tools) or when to skip recording. No prerequisites, no exclusions, no alternatives are named.

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. "Save" implies a persistent mutation, but nothing states whether writes are idempotent, whether duplicate facts are merged or duplicated, whether existing entries can be overwritten, or what identifier comes back. For a memory-write tool with zero annotation coverage, this leaves 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 front-loaded sentence with no filler; the verb leads and the accepted content types follow. It is efficient, though it stops short of the second sentence that would carry the missing usage and behavioral context.

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, the description is the only place to learn how this write behaves and what it returns, and it says nothing about either. For a mutation tool in a memory system with three sibling tools, the definition is under-specified relative to its complexity.

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 100%, so content, category, and salience are already fully documented, including the enum values and the 0.95+ salience guidance. The description's type list loosely echoes the category enum but adds no syntax, formatting, or content-granularity guidance beyond the schema. Baseline 3 is appropriate.

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?

"Save an atomic fact, architectural decision, permanent directive, or SOP" gives a specific verb and enumerates the resource types, which the opaque name "synapse_retain" does not convey on its own. It is clear what the tool does, but it never contrasts itself with the sibling synapse_record_episode, which by name plausibly also writes to the same memory store.

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 enumerated content types (atomic fact, decision, directive, SOP) implicitly scope when to use this tool, and the word "atomic" hints at granularity. But there is no explicit statement of when to prefer synapse_recall, synapse_record_episode, or synapse_get_stats, and no guidance on deduplication or repeat saves.

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