Skip to main content
Glama
AstralVoidZ
by AstralVoidZ

ppsspp_breakpoint

Manage CPU execution and memory watchpoints for active PPSSPP sessions. Set, remove, update, or list breakpoints to pause on specific code or memory access, enabling targeted debugging of PSP games.

Instructions

PURPOSE: Set, remove, update, and list CPU execution breakpoints and memory watchpoints.

USAGE: action + session_id; set/remove/update manage CPU exec breakpoints (address required); mem_set/mem_remove/mem_update manage memory watchpoints (size 1/2/4+, read/write flags); list/mem_list take no address.

BEHAVIOR: MUTATING. Reliable hits need CPUCore=2 (IR Interpreter). mem_remove resolves the watchpoint's real size via mem_list first (address+size matching); mem_update merges existing read/write/change unconditionally (PPSSPP zero-omits omitted bools). CPU set/remove return no data — the tool follows with a list for verification.

RETURNS: {action, address, enabled, breakpoints[]}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
logNoLog flag (update / mem_set / mem_update only; None = don't change). For mem_set, defaults to False when None.
readNoTrigger on read access (mem_set only; None defaults to True). For mem_update, passing read triggers a merge query — omit to leave read unchanged.
sizeNoMemory breakpoint watch size in bytes (mem_set / mem_remove / mem_update; default 4). Fixed-width watches use 1/2/4; larger sizes are passed through to PPSSPP as a range watch. PPSSPP matches memory breakpoints by address+size pair, so remove/update must pass the exact size recorded at set time.
writeNoTrigger on write access (mem_set only; None defaults to True). For mem_update, passing write triggers a merge query — omit to leave write unchanged.
actionYesBreakpoint operation. Valid values: CPU breakpoint actions: - 'set': add a CPU execution breakpoint (requires address; enabled? defaults to True; condition? optional). - 'remove': delete a CPU breakpoint by address. - 'list': list all current CPU breakpoints. - 'update': update a CPU breakpoint's enabled/log/condition/log_format (requires address; all other params optional). Memory breakpoint actions: - 'mem_set': add a memory access breakpoint (requires address; size?/read?/write?/enabled?/log?/condition?/log_format?). - 'mem_remove': delete a memory breakpoint by address. Delete semantics are STRICT: removing a non-existent memcheck is an ERROR (unlike ppsspp_state_observer action=clear, which is idempotent-ok — F-5 contract, 2026-09-08). - 'mem_list': list all current memory breakpoints. - 'mem_update': update a memory breakpoint's enabled/log/condition/log_format (requires address).
addressNoBreakpoint address, as a hex string (e.g. '0x08804000'). Required for set / remove / update / mem_set / mem_remove / mem_update; ignored for list / mem_list.0x0
enabledNoBreakpoint enable flag. For action='set' / 'mem_set', defaults to True when None. For action='update' / 'mem_update', None means 'don't change'. Ignored for remove / list actions.
conditionNoBreak condition expression (set / update / mem_set / mem_update; None = don't send).
log_formatNoLog format string (update / mem_set / mem_update only; None = don't change).
session_idYesActive session ID.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYes'set' / 'remove' / 'list' / 'update' / 'mem_set' / 'mem_remove' / 'mem_list' / 'mem_update'.
addressYesBreakpoint address, hex string (e.g. '0x08804000'); '0x00000000' for list / mem_list.
enabledYesEnabled flag (set / mem_set / update / mem_update only).
breakpointsYesBreakpoint list (list / mem_list only).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

The description is marked 'MUTATING' and explains important behavioral details: 'Reliable hits need CPUCore=2 (IR Interpreter)', 'mem_remove resolves the watchpoint's real size via mem_list first', and 'mem_update merges existing read/write/change unconditionally (PPSSPP zero-omits omitted bools)'. It also notes that CPU set/remove return no data. These are critical behavioral insights beyond the annotations, which are minimal (no readOnly, no idempotent, no destructive hints). The description compensates fully.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with labeled sections (PURPOSE, USAGE, BEHAVIOR, RETURNS). It is compact yet information-dense, with each sentence serving a purpose. The front-loaded PURPOSE and USAGE sections quickly orient the agent. No filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (10 parameters, multiple actions), the description covers essential aspects: purpose, usage patterns, behavioral caveats (CPUCore requirement, size matching, merge semantics), and return shape. The output schema exists, so return details are already structured. The description is complete enough for an agent to call the tool correctly without surprises.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema documents all parameters in detail. The description adds a summary of action semantics and the crucial note about size matching for remove/update. It also clarifies that for mem_update, passing read/write triggers a merge query. This adds meaning beyond the schema, especially the merger behavior and size matching caveat. A slight deduction because not all parameters are described in the description, but the schema is thorough.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Set, remove, update, and list CPU execution breakpoints and memory watchpoints.' It uses specific verbs and resources, distinguishing between CPU execution breakpoints and memory watchpoints. The sibling tools are mostly unrelated (memory read/write, stepping, etc.), so this tool stands out as the breakpoint manager.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly instructs how to use the tool: 'action + session_id', and details which actions manage which type of breakpoint. It also notes that 'list/mem_list take no address' and that 'CPU set/remove return no data—the tool follows with a list for verification.' This gives clear usage context and differentiates between CPU and memory variants, though it doesn't explicitly mention when to choose this over siblings, but the purpose is unique enough.

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