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 discloses that the operation writes into a destination session store and that formats are converted, but it says nothing about whether an existing session there is overwritten, what permissions/auth are needed, or whether the injection is reversible. For a write-style 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 sentence with the action verb front-loaded and no filler; the parenthetical agent list is compact. It earns nearly all of its length, though the long clause structure is slightly dense.

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 must stand alone. It conveys the core action and destination set, and 'latest context bundle' implicitly justifies the optional source parameters, but it omits side effects, overwrite behavior, and prerequisites — leaving real gaps for a mutating tool.

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 100%, with all four parameters documented in the schema, and the description's parenthetical agent list merely repeats the to_agent enum. It adds no syntax, defaulting, or format detail beyond what the schema already supplies, so the baseline 3 applies.

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 compound verb (convert and inject) and a precise resource (the latest context bundle into a target agent's native session store), and it enumerates the valid destination agents. It does not explicitly name or contrast a sibling (e.g., pull_handoff_context), 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 trailing clause 'so it can be resumed natively' implies the situation in which to reach for this tool, but there is no explicit when-to-use statement, no exclusion, and no named alternative among the handoff/session siblings. Usage is inferable but not guided.

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 must carry the behavioral burden; it does disclose the return fields (session IDs, titles, working directories, turn counts, timestamps), which is genuine content. It never states that this is a read-only, non-mutating operation, nor anything about pagination or the semantics of 'recent'.

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 filler. Because there is no output schema, the enumeration of returned fields is load-bearing rather than redundant, and nothing could be cut without losing signal.

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 simple, zero-required-parameter list tool with no output schema, the description covers platforms and return fields adequately. The remaining gaps are the undefined 'recent' window and any pagination/ordering behavior, which an agent would want before relying on the result set.

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 three parameters (cwd, agent, limit) are already documented in the schema. The description only obliquely echoes them via 'working directories' and the platform list; it adds no syntax, default, or format detail beyond what the schema provides, so the baseline 3 applies.

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 (List) and resource (recent coding sessions) and enumerates the four platforms covered plus the fields returned, so the agent knows exactly what comes back. It does not, however, name or contrast itself with the sibling search_cross_agent_history, which is the tool most likely to be confused with a listing call.

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 exclusions, and no mention of when to prefer search_cross_agent_history or pull_handoff_context instead. The word 'recent' is the only scoping cue and is never defined (window, sort order, or relationship to the limit default of 15).

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 and no output schema, the description carries the full disclosure burden, and it does most of that work: it details the returned content (verbatim turns, plans, checklists, file lists, terminal errors, git state) and the extra cross-platform snapshot. It does not state the operation is read-only/non-mutating, nor mention any size, rate, or truncation limits beyond the max_turns parameter, leaving a modest 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?

Two sentences, front-loaded with the core action, and the long parenthetical enumeration of returned artifacts is information-dense rather than padding. It is slightly heavy in one sentence, but every element earns its place by telling the agent what it gets back.

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 read tool with no annotations and no output schema, the description supplies the return-content inventory an agent needs to decide whether calling it is worthwhile, plus trigger phrases. Remaining gaps — read-only guarantee, truncation/limits behavior, and how the cross-platform snapshot relates to the primary result — are minor but real.

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 with examples and defaults. The description adds no parameter-level syntax, format, or interaction guidance beyond what the schema provides, so the baseline 3 applies.

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 opens with a specific verb+resource ('Pull the exact context ... from the user's previous session') and enumerates exactly what that context contains: verbatim turns, plans, checklists, files, commands/errors, git state. It also names the supported source platforms and a secondary behavior (cross-platform session snapshot), which distinguishes it from list_recent_sessions and search_cross_agent_history.

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?

It gives concrete invocation triggers — literal strings like '/handoff', '$handoff', 'continue from my last session', and the agent-switch scenario. That is strong when-to-use guidance. It stops short of naming sibling tools as alternatives or stating when NOT to use it (e.g., versus search_cross_agent_history), so it's clear but not fully 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?

With no annotations, the description carries the full behavioral burden. It does disclose the downstream effect (the note surfaces at the top of the next agent's handoff context), which is genuinely useful, but says nothing about persistence scope, whether repeated saves overwrite, or any permission 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?

A single sentence that front-loads the action and closes with the payoff for the next agent. No filler, no restatement of the 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 simple 3-parameter tool with full schema coverage and no output schema, the description covers what it does and why it matters. The remaining gaps – overwrite/repeat-save semantics and whether cwd is required to target a workspace – are modest but real for a write tool.

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 cwd, summary, and next_steps in detail; baseline is 3. The description names 'summary and next steps' but adds no new meaning beyond the schema and says nothing about the cwd parameter's role in scoping the checkpoint.

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?

Specific verb+resource ('Save an explicit checkpoint summary and next steps') plus the observable effect on the next agent's handoff context. It implicitly contrasts with the read-side sibling pull_handoff_context, but never names it or the other siblings, so differentiation is left to the agent.

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 'so the next agent you open receives it' – i.e. call this before handing off – but there is no explicit when-to-use, when-not-to-use, or statement of alternatives such as inject_session_to_agent or pull_handoff_context.

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 breadth of data searched (four agents plus transcripts, plans, and file paths), which is genuine behavioral context, but it omits match semantics (substring vs. semantic), case sensitivity, result shape, and whether every agent is always indexed.

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?

One sentence, front-loaded with the verb and scope, with zero filler. Every clause earns its place by specifying what is searched and where.

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 simple read-only search with no output schema and no annotations, the definition covers scope and inputs adequately but says nothing about what a result contains or how matches are grouped or ranked. An agent could call it correctly, but the return behavior is left entirely 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?

Schema description coverage is 100%, so all three parameters are already documented in the schema; baseline 3 applies. The description's restatement of acceptable query values (keyword, error message, filename) mildly reinforces the query parameter but adds no syntax or format detail beyond it.

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), a clear scope (across all 4 agents), and the exact content types searched (conversation transcripts, plans, modified file paths). It is easily distinguished from siblings like save_checkpoint_note or inject_session_to_agent, which perform entirely different operations.

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 by naming the search inputs (keyword, error message, filename), which conveys a retrieval scenario. However, it names no alternative tool and gives no explicit when-not-to-use conditions, leaving routing to inference.

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