MIHAD

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 important cascading effect that derived items are also suspended. However, it leaves key behavioral questions open: whether suspension is reversible, whether it requires special authorization, and whether 'suspended' means deleted or merely flagged.

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, front-loaded sentences with no wasted words; the consequential cascade behavior is stated immediately after the core action.

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 two-parameter mutation tool with no annotations and no output schema, the description covers the core action and the important derived-item consequence, but omits reversibility, permission requirements, and any indication of what the caller gets back.

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 both 'id' and 'reason' are undocumented in structured fields and the description adds nothing about them. The parameter names are largely self-explanatory, but the description does not clarify what identifier format is expected or how the reason is used.

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 ('Mark ... as wrong') and resource ('a memory item'), which is clearly distinct from the recall/propose/report_outcome siblings. It does not explicitly name how it differs from those siblings, but the action is unambiguous.

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 use this versus memory_report_outcome or the other siblings, and no prerequisites or conditions are stated. Usage is only implied by 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?

No annotations exist, so the description carries the full burden. It usefully discloses lifecycle behavior ('kind=lesson... stays provisional until a human approves it', 'Only adopted items count as verified knowledge'), which goes beyond the schema. It says nothing about side effects, persistence timing, permissions, or what a proposal returns, leaving significant behavioral gaps for an un-annotated write 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 core purpose is front-loaded in the first sentence, and the remaining semicolon-separated clauses are dense but each carries distinct kind semantics. There is some redundancy with the schema's verify description, which prevents a 5.

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 7-parameter tool with a nested object and no output schema, the description covers the essential model: the four kinds, how each is verified, and the adoption/provisional lifecycle. It omits relationship semantics (supersedes/derived_from) and any routing versus sibling memory tools, so it is solid but not exhaustive.

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 57% and the nested verify object already documents the per-kind shape ({command, test_files}, {file, quote}, {quote}). The description's verification sentences largely restate that schema text rather than adding syntax or format detail. Tags, title, supersedes, and derived_from get no elaboration in the description.

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+resource ('Propose something worth remembering for future sessions') and then enumerates the four kinds (skill, fact, preference, lesson), so the agent knows exactly what the tool produces. It does not explicitly contrast itself with the siblings memory_recall, memory_correct, or memory_report_outcome, which keeps it just below 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 per-kind clauses give clear conditions for choosing each kind ('kind=skill: a reusable technique or code pattern... kind=fact: a fact about this codebase...'), effectively telling the agent when each mode applies. However, there is no guidance on when to use this tool rather than memory_correct or memory_recall, and no exclusion criteria.

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 burden and does well: it discloses the trust hierarchy (verified vs. provisional/unverified treated as hints only) and instructs that 'preferences' be followed. It does not state permission/auth requirements or rate limits, but for a read tool the output-semantics disclosure is substantive.

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?

Four sentences, front-loaded with the action and timing, then return semantics and caveats. Dense with useful information and no filler, though the 'preferences' instruction could be folded more tightly.

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 output schema and no annotations, the description adequately explains what comes back (verified skills, facts, lessons, preferences) and how to treat unverified items. The gap is the unexplained 'k' parameter and any limits on result volume.

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 'query' has schema documentation (coverage 50%); 'k' is undocumented in both schema and description, and the description never mentions result count or how to control it. The phrase 'what you are about to work on' loosely aligns with query but adds little 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 ('Search') and resource ('the project's persistent memory') and clarifies the return contents (verified skills, facts, lessons). It does not explicitly contrast itself with the write-oriented siblings (memory_propose, memory_correct, memory_report_outcome), though the read/search nature is inherently distinct.

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?

'Search the project's persistent memory before starting work' gives a clear triggering context. No when-not conditions or named alternatives are given, so it falls short of full 5-level routing guidance.

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 disclosure burden. It mentions reporting helpful or harmful items, but doesn't explain what happens with that data (e.g., is it used to update memory? are there consequences?). It doesn't state permissions, reversibility, or side effects. For a tool that likely influences a memory system, this is a notable 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?

The description is a single, well-structured sentence that front-loads the timing and action. Every word earns its place; there is no redundancy or filler.

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?

Given 6 parameters with 0% schema description coverage, no annotations, and no output schema, the description is far too sparse. It doesn't clarify parameter usage, expected data formats, or behavioral consequences. It leaves the agent with significant ambiguity about how to correctly populate the fields (e.g., what constitutes 'used' vs 'helpful' vs 'harmful', how task_id relates, what notes should contain).

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 only vaguely alludes to a subset of parameters ('used memory items,' 'helped or caused problems'). With 6 parameters including success, notes, task_id, used_ids, helpful_ids, harmful_ids, the description does not explain the meaning, format, or relationships of these parameters. An agent would need to infer from parameter names alone, which is insufficient given the zero schema coverage.

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+resource ('report which memory items you used') and its timing ('at the end of a task'). It is reasonably distinct from siblings like memory_recall and memory_correct, though it doesn't explicitly name them. The purpose is clear: a feedback mechanism for memory usage.

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 provides a clear usage condition: 'At the end of a task.' This tells the agent when to call it. It doesn't explicitly exclude other times or name alternatives, but the timing constraint is a strong usage guideline. No misleading guidance is present.

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